CVPR2026｜底层视觉(超分辨率，图像恢复，去雨，去雾，去模糊，去噪等)相关论文汇总（附论文链接/开源代码）【持续更新】

Kobaayyy2026-06-03 12:52

CVPR2026｜底层视觉相关论文汇总（如果觉得有帮助，欢迎点赞和收藏）

  • 1.超分辨率(Super-Resolution)
      • xxx
      • [AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution](#AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution)
      • [Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution](#Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution)
      • [CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness](#CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness)
      • [Compressed-Domain-Aware Online Video Super-Resolution](#Compressed-Domain-Aware Online Video Super-Resolution)
      • [Disentangled Textual Priors for Diffusion-based Image Super-Resolution](#Disentangled Textual Priors for Diffusion-based Image Super-Resolution)
      • [DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution](#DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution)
      • [DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer](#DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer)
      • [DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution](#DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution)
      • [Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution](#Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution)
      • [DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution](#DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution)
      • [DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolution](#DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolution)
      • [Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution](#Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution)
      • [Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation](#Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation)
      • [Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning](#Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning)
      • [FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution](#FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution)
      • [FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution](#FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution)
      • [FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution](#FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution)
      • [GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution](#GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution)
      • [Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution](#Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution)
      • [HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution](#HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution)
      • [IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution](#IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution)
      • [IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution](#IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution)
      • [Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution](#Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution)
      • [LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution](#LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution)
      • [One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution](#One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution)
      • [Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction](#Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction)
      • [Plug-and-Play Dynamic In-context Learning with Stochastic Regularization for Screen Content Image Super-Resolution](#Plug-and-Play Dynamic In-context Learning with Stochastic Regularization for Screen Content Image Super-Resolution)
      • [PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion](#PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion)
      • [QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution](#QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution)
      • [RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution](#RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution)
      • [Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework](#Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework)
      • [Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance](#Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance)
      • [Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features](#Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features)
      • [SAT: Selective Aggregation Transformer for Image Super-Resolution](#SAT: Selective Aggregation Transformer for Image Super-Resolution)
      • [Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization](#Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization)
      • [SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting](#SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting)
      • [STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution](#STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution)
      • [TextOVSR: Text-Guided Real-World Opera Video Super-Resolution](#TextOVSR: Text-Guided Real-World Opera Video Super-Resolution)
      • [Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors](#Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors)
      • [Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution](#Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution)
      • [Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution](#Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution)
      • [TinySR: Shallow Diffusion Transformers for Real-World Image Super-Resolution](#TinySR: Shallow Diffusion Transformers for Real-World Image Super-Resolution)
      • [Towards Real-Time Diffusion-Based Streaming Video Super-Resolution](#Towards Real-Time Diffusion-Based Streaming Video Super-Resolution)
      • [Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset](#Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset)
      • [TPTransformer: Tensor-Tensor Product Transformer for Hyperspectral Image Super-Resolution](#TPTransformer: Tensor-Tensor Product Transformer for Hyperspectral Image Super-Resolution)
      • [TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution](#TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution)
      • [UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution](#UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution)
      • [VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment](#VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment)
      • [VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution](#VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution)
      • [VOSR: A Vision-Only Generative Model for Image Super-Resolution](#VOSR: A Vision-Only Generative Model for Image Super-Resolution)
  • [2.图像去雨(Image Deraining)](#2.图像去雨(Image Deraining))
      • [UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization](#UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization)
      • [Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy](#Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy)
  • [3.图像去雾(Image Dehazing)](#3.图像去雾(Image Dehazing))
      • [Bilevel Layer-Positioning LoRA for Real Image Dehazing](#Bilevel Layer-Positioning LoRA for Real Image Dehazing)
      • [Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus](#Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus)
      • [From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing](#From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing)
      • [HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching](#HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching)
      • [Inf-Dehaze: Beyond GPU Memory Constraints for Ultra-High-Resolution Image Dehazing](#Inf-Dehaze: Beyond GPU Memory Constraints for Ultra-High-Resolution Image Dehazing)
  • 4.去模糊(Deblurring)
      • [BluRef: Unsupervised Image Deblurring with Dense-Matching References](#BluRef: Unsupervised Image Deblurring with Dense-Matching References)
      • [Event-based Motion Deblurring with Unpaired Data](#Event-based Motion Deblurring with Unpaired Data)
      • [Gyro-based Deep Video Deblurring](#Gyro-based Deep Video Deblurring)
      • [Motion-Aware Animatable Gaussian Avatars Deblurring](#Motion-Aware Animatable Gaussian Avatars Deblurring)
      • [MSCD-GS: Motion-Separated Cooperative Deblurring Dynamic Reconstruction via Gaussian Splatting](#MSCD-GS: Motion-Separated Cooperative Deblurring Dynamic Reconstruction via Gaussian Splatting)
      • [MVSSM: Motion-aware Visual State Space Model for Efficient Video Deblurring](#MVSSM: Motion-aware Visual State Space Model for Efficient Video Deblurring)
      • [OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring](#OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring)
      • [SelfHVD: Self-Supervised Handheld Video Deblurring](#SelfHVD: Self-Supervised Handheld Video Deblurring)
      • [Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor](#Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor)
      • [Unblur-SLAM: Dense Neural SLAM for Blurry Inputs](#Unblur-SLAM: Dense Neural SLAM for Blurry Inputs)
  • 5.去噪(Denoising)
      • [2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition](#2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition)
      • [Back to Basics: Let Denoising Generative Models Denoise](#Back to Basics: Let Denoising Generative Models Denoise)
      • [Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising](#Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising)
      • [Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning](#Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning)
      • [Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices](#Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices)
      • [Learning to Translate Noise for Robust Image Denoising](#Learning to Translate Noise for Robust Image Denoising)
      • [LF-BVN: Blind-View Network for Self-Supervised Light Field Denoising](#LF-BVN: Blind-View Network for Self-Supervised Light Field Denoising)
      • [Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising](#Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising)
      • [RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference](#RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference)
      • [Routing on Demand: DSNet for Efficient Progressive Point Cloud Denoising](#Routing on Demand: DSNet for Efficient Progressive Point Cloud Denoising)
      • [Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging](#Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging)
      • [TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Denoising](#TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Denoising)
      • [Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation](#Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation)
  • [6.图像恢复(Image Restoration)](#6.图像恢复(Image Restoration))
      • [Benchmarking Endoscopic Surgical Image Restoration and Beyond](#Benchmarking Endoscopic Surgical Image Restoration and Beyond)
      • [Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration](#Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration)
      • [Beyond the Ground Truth: Enhanced Supervision for Image Restoration](#Beyond the Ground Truth: Enhanced Supervision for Image Restoration)
      • [Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration](#Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration)
      • [Blockwise Divide-and-Aggregate for Image Restoration using Diffusion Priors](#Blockwise Divide-and-Aggregate for Image Restoration using Diffusion Priors)
      • [CARD: Correlation Aware Restoration with Diffusion](#CARD: Correlation Aware Restoration with Diffusion)
      • [DEBIR: Dynamic Exposure Burst Image Restoration](#DEBIR: Dynamic Exposure Burst Image Restoration)
      • [Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration](#Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration)
      • [DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping](#DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping)
      • [EpiAgent: An Agent-Centric System for Ancient Inscription Restoration](#EpiAgent: An Agent-Centric System for Ancient Inscription Restoration)
      • [Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration](#Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration)
      • [Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration](#Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration)
      • [FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration](#FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration)
      • [FlowSteer: Conditioning Flow Field for Consistent Image Restoration](#FlowSteer: Conditioning Flow Field for Consistent Image Restoration)
      • [FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model](#FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model)
      • [Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery](#Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery)
      • [gQIR: Generative Quanta Image Reconstruction](#gQIR: Generative Quanta Image Reconstruction)
      • [GSNR: Graph Smooth Null-Space Representation for Inverse Problems](#GSNR: Graph Smooth Null-Space Representation for Inverse Problems)
      • [HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration](#HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration)
      • [How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices](#How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices)
      • [Hybrid Agents for Image Restoration](#Hybrid Agents for Image Restoration)
      • [LWTformer: A Detail-Aware, Learnable Wavelet-Transformer for Ancient Chinese Character Image Restoration](#LWTformer: A Detail-Aware, Learnable Wavelet-Transformer for Ancient Chinese Character Image Restoration)
      • [MMDIR: Multimodal Instruction-Driven Framework for Mixed-Degradation Document Image Restoration](#MMDIR: Multimodal Instruction-Driven Framework for Mixed-Degradation Document Image Restoration)
      • [NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration](#NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration)
      • [Optical Tolerance-Compensated Diffusion Model for Image Restoration](#Optical Tolerance-Compensated Diffusion Model for Image Restoration)
      • [PGDR-BambooSlips: Physics-Guided Multistep Deformation Reversal for Ancient Bamboo Slip Restoration](#PGDR-BambooSlips: Physics-Guided Multistep Deformation Reversal for Ancient Bamboo Slip Restoration)
      • [Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration](#Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration)
      • [RDBM: Residual Diffusion Bridge Model for Image Restoration](#RDBM: Residual Diffusion Bridge Model for Image Restoration)
      • [Residual Diffusion Bridge Model for Image Restoration](#Residual Diffusion Bridge Model for Image Restoration)
      • [Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback](#Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback)
      • [Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration](#Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration)
      • [Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank](#Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank)
      • [Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration](#Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration)
      • [Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration](#Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration)
      • [ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration](#ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration)
      • [Surgical Image Restoration Benchmark](#Surgical Image Restoration Benchmark)
      • [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](#UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement)
      • [UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration](#UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration)
      • [UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration](#UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration)
      • [UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration](#UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration)
      • [VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration](#VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration)
      • [ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models](#ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models)
  • [7.图像增强(Image Enhancement)](#7.图像增强(Image Enhancement))
      • [Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement](#Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement)
      • [Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancement](#Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancement)
      • [BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement](#BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement)
      • [CtrlISP: Rescuing Low-Light RAW Images via Controllable Neural ISP](#CtrlISP: Rescuing Low-Light RAW Images via Controllable Neural ISP)
      • [EIC-LIE: Event-Illumination Collaborative Low-light Image Enhancement](#EIC-LIE: Event-Illumination Collaborative Low-light Image Enhancement)
      • [Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels](#Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels)
      • [Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset](#Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset)
      • [IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images](#IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images)
      • [Leveraging Multispectral Sensors for Color Correction in Mobile Cameras](#Leveraging Multispectral Sensors for Color Correction in Mobile Cameras)
      • [MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior](#MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior)
      • [Multinex: Lightweight Low-Light Image Enhancement via Multi-prior Retinex](#Multinex: Lightweight Low-Light Image Enhancement via Multi-prior Retinex)
      • [NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness](#NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness)
      • [PrismNet: Semantic-Aware Image Enhancement via Vision Transformer and Zero-Cost Gating](#PrismNet: Semantic-Aware Image Enhancement via Vision Transformer and Zero-Cost Gating)
      • [RodNet: Visual Pathway-Inspired Adaptive Sparse Network for Efficient Low-Light Image Enhancement](#RodNet: Visual Pathway-Inspired Adaptive Sparse Network for Efficient Low-Light Image Enhancement)
      • [SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control](#SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control)
      • [Towards Generalized Representations for Low-Light Understanding: When Signal Constancy Meets Semantic Enrichment](#Towards Generalized Representations for Low-Light Understanding: When Signal Constancy Meets Semantic Enrichment)
      • [VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment](#VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment)
  • 8.图像修复(Inpainting)
      • [Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting](#Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting)
      • [DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos](#DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos)
      • [EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing](#EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing)
      • [From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition](#From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition)
      • [GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space](#GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space)
      • [HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images](#HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images)
      • [InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting](#InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting)
      • [LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors](#LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors)
      • [MAGIC: Few-Shot Mask-Guided Anomaly Inpainting](#MAGIC: Few-Shot Mask-Guided Anomaly Inpainting)
      • [Object-WIPER: Training-Free Object and Associated Effect Removal in Video](#Object-WIPER: Training-Free Object and Associated Effect Removal in Video)
      • [PHAC: Promptable Human Amodal Completion](#PHAC: Promptable Human Amodal Completion)
      • [Precise Object and Effect Removal with Adaptive Target-Aware Attention](#Precise Object and Effect Removal with Adaptive Target-Aware Attention)
      • [YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal](#YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal)
  • [9.高动态范围成像(HDR Imaging)](#9.高动态范围成像(HDR Imaging))
      • [Beyond8Bits: Full HDR UGC Dataset](#Beyond8Bits: Full HDR UGC Dataset)
      • [ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction](#ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction)
      • [F²HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](#F²HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling)
      • [LRHDR: Learning Representation-enhanced HDR Video Reconstruction](#LRHDR: Learning Representation-enhanced HDR Video Reconstruction)
      • [Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments](#Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments)
        • [Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events](#Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events)
  • [10.图像质量评价(Image Quality Assessment)](#10.图像质量评价(Image Quality Assessment))
      • [A^3: Towards Advertising Aesthetic Assessment](#A^3: Towards Advertising Aesthetic Assessment)
      • [ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding](#ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding)
      • [Bridging the Perception Gap in Image Super-Resolution Evaluation](#Bridging the Perception Gap in Image Super-Resolution Evaluation)
      • [Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks](#Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks)
      • [FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy](#FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy)
      • [Generalizable Video Quality Assessment via Weak-to-Strong Learning](#Generalizable Video Quality Assessment via Weak-to-Strong Learning)
      • [HDR-VLM: HDR-Domain Adaptation of VLMs and Preference-Aligned Quality Assessment for HDR Video Color Grading](#HDR-VLM: HDR-Domain Adaptation of VLMs and Preference-Aligned Quality Assessment for HDR Video Color Grading)
      • [Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency](#Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency)
      • [Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling](#Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling)
      • [MDS-VQA: Model-Informed Data Selection for Video Quality Assessment](#MDS-VQA: Model-Informed Data Selection for Video Quality Assessment)
      • [Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline](#Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline)
      • [Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment](#Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment)
      • [PR-IQA: Partial-Reference Image Quality Assessment for Diffusion Models](#PR-IQA: Partial-Reference Image Quality Assessment for Diffusion Models)
      • [QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment](#QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment)
      • [Rethinking Knowledge Transfer in Image Quality Assessment: A Perceptual Preference Structure Alignment Perspective](#Rethinking Knowledge Transfer in Image Quality Assessment: A Perceptual Preference Structure Alignment Perspective)
      • [RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360° Image Quality Assessment](#RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360° Image Quality Assessment)
      • [rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training](#rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training)
      • [Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos](#Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos)
      • [VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment](#VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment)
  • [11.插帧(Frame Interpolation)](#11.插帧(Frame Interpolation))
      • [Anchoring and Rescaling Attention for Semantically Coherent Inbetweening](#Anchoring and Rescaling Attention for Semantically Coherent Inbetweening)
      • [LDF-VFI: Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers](#LDF-VFI: Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers)
      • [One-Shot Flow, Any-Time Frame: A Bidirectional Warping Framework for Event-Based Video Frame Interpolation](#One-Shot Flow, Any-Time Frame: A Bidirectional Warping Framework for Event-Based Video Frame Interpolation)
      • [Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers](#Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers)
  • [12.视频/图像压缩(Video/Image Compression)](#12.视频/图像压缩(Video/Image Compression))
      • [Adaptive Learned Image Compression with Graph Neural Networks](#Adaptive Learned Image Compression with Graph Neural Networks)
      • [Beyond Pixel Loss: Video-INRs Prefer Perceptual Optimization](#Beyond Pixel Loss: Video-INRs Prefer Perceptual Optimization)
      • [Block-based Learned Image Compression without Blocking Artifacts](#Block-based Learned Image Compression without Blocking Artifacts)
      • [CADC: Content Adaptive Diffusion-Based Generative Image Compression](#CADC: Content Adaptive Diffusion-Based Generative Image Compression)
      • [CoD: A Diffusion Foundation Model for Image Compression](#CoD: A Diffusion Foundation Model for Image Compression)
      • [Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression](#Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression)
      • [Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates](#Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates)
      • [DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression](#DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression)
      • [FreqSIC: Frequency-aware Stereo Image Compression with Bi-directional Checkerboard Context Model](#FreqSIC: Frequency-aware Stereo Image Compression with Bi-directional Checkerboard Context Model)
      • [Generative Neural Video Compression via Video Diffusion Prior](#Generative Neural Video Compression via Video Diffusion Prior)
      • [Generative Video Compression with One-Dimensional Latent Representation](#Generative Video Compression with One-Dimensional Latent Representation)
      • [Learned Image Compression via Sparse Attention and Adaptive Frequency](#Learned Image Compression via Sparse Attention and Adaptive Frequency)
      • [Low-Bitrate Video Compression through Semantic-Conditioned Diffusion](#Low-Bitrate Video Compression through Semantic-Conditioned Diffusion)
      • [MambaSIC: Mamba-based Stereo Image Compression with Bi-directional Multi-reference Entropy Model](#MambaSIC: Mamba-based Stereo Image Compression with Bi-directional Multi-reference Entropy Model)
      • [OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data](#OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data)
      • [Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression](#Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression)
      • [Perceptual Neural Video Compression with Color Separation and Rank Chain](#Perceptual Neural Video Compression with Color Separation and Rank Chain)
      • [Real-Time Neural Video Compression with Unified Intra and Inter Coding](#Real-Time Neural Video Compression with Unified Intra and Inter Coding)
      • [Ultra-Fast Neural Video Compression](#Ultra-Fast Neural Video Compression)
      • [Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder](#Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder)
      • [VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression](#VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression)
      • [What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters](#What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters)
      • [What Matters in Practical Learned Image Compression](#What Matters in Practical Learned Image Compression)
  • [13.压缩图像/视频质量增强(Compressed Image/Video Quality Enhancement)](#13.压缩图像/视频质量增强(Compressed Image/Video Quality Enhancement))
  • [14.图像去反光(Image Reflection Removal)](#14.图像去反光(Image Reflection Removal))
      • [GenSIRR: Rectifying Latent Space for Generative Single-Image Reflection Removal](#GenSIRR: Rectifying Latent Space for Generative Single-Image Reflection Removal)
      • [GFRRN: Explore the Gaps in Single Image Reflection Removal](#GFRRN: Explore the Gaps in Single Image Reflection Removal)
      • [LightRR: A Lightweight Network for Single Image Reflection Removal](#LightRR: A Lightweight Network for Single Image Reflection Removal)
      • [Polarization State Tracing for Reflection Removal and Color-Consistent Reconstruction](#Polarization State Tracing for Reflection Removal and Color-Consistent Reconstruction)
      • [Rectifying Latent Space for Generative Single-Image Reflection Removal](#Rectifying Latent Space for Generative Single-Image Reflection Removal)
      • [Reflection Separation from a Single Image via Joint Latent Diffusion](#Reflection Separation from a Single Image via Joint Latent Diffusion)
      • [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](#ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation)
  • [15.图像去阴影(Image Shadow Removal)](#15.图像去阴影(Image Shadow Removal))
      • [PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors](#PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors)
  • [16.图像上色(Image Colorization)](#16.图像上色(Image Colorization))
      • [ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization](#ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization)
      • [SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation](#SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation)
      • [Towards High-resolution and Disentangled Reference-based Sketch Colorization](#Towards High-resolution and Disentangled Reference-based Sketch Colorization)
  • [17.图像和谐化(Image Harmonization)](#17.图像和谐化(Image Harmonization))
      • [HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition](#HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition)
      • [HarmoVid: Relightful Video Portrait Harmonization](#HarmoVid: Relightful Video Portrait Harmonization)
  • [18.视频稳相(Video Stabilization)](#18.视频稳相(Video Stabilization))
      • [LightStab: Unsupervised Online Video Stabilization with Classical Priors](#LightStab: Unsupervised Online Video Stabilization with Classical Priors)
      • [No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors](#No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors)
      • [StabiGS: Video Stabilization through Rendering-Aware Trajectory Optimization in 3DGS-Reconstructed Scenes](#StabiGS: Video Stabilization through Rendering-Aware Trajectory Optimization in 3DGS-Reconstructed Scenes)
  • [19.图像融合(Image Fusion)](#19.图像融合(Image Fusion))
      • [Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion](#Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion)
      • [Bridging Human Evaluation to Infrared and Visible Image Fusion](#Bridging Human Evaluation to Infrared and Visible Image Fusion)
      • [Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion](#Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion)
      • [Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios](#Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios)
      • [Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization](#Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization)
      • [FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration](#FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration)
      • [More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization](#More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization)
      • [Multi-Modal Image Fusion via Intervention-Stable Feature Learning](#Multi-Modal Image Fusion via Intervention-Stable Feature Learning)
      • [Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared](#Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared)
      • [Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion](#Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion)
      • [PhyFusion: Physics-Aware Infrared and Visible Image Fusion via Modality-Specific Physical Priors](#PhyFusion: Physics-Aware Infrared and Visible Image Fusion via Modality-Specific Physical Priors)
      • [ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling](#ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling)
      • [RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion](#RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion)
      • [UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation](#UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation)
      • [VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration](#VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration)
  • 20.其他任务(Others)
        • [3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion](#3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion)
      • [AceTone: Bridging Words and Colors for Conditional Image Grading](#AceTone: Bridging Words and Colors for Conditional Image Grading)
      • [Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis](#Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis)
        • [Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark](#Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark)
      • [CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration](#CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration)
        • [D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping](#D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping)
      • [Dark3R: Learning Structure from Motion in the Dark](#Dark3R: Learning Structure from Motion in the Dark)
      • [Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement](#Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement)
      • [Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models](#Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models)
      • [Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark](#Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark)
      • [FastGaMer: Efficient GainMap Learning for Practical Inverse Tone Mapping](#FastGaMer: Efficient GainMap Learning for Practical Inverse Tone Mapping)
      • [Fast Kernel-Space Diffusion for Remote Sensing Pansharpening](#Fast Kernel-Space Diffusion for Remote Sensing Pansharpening)
      • [HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter](#HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter)
      • [High-Quality and Efficient Turbulence Mitigation with Events](#High-Quality and Efficient Turbulence Mitigation with Events)
      • [InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space](#InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space)
      • [It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal](#It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal)
      • [JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization](#JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization)
      • [Language-Guided One-Step Diffusion Model for Nighttime Flare Removal](#Language-Guided One-Step Diffusion Model for Nighttime Flare Removal)
      • [Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal](#Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal)
      • [LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging](#LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging)
      • [MERIT: Multi-domain Efficient RAW Image Translation](#MERIT: Multi-domain Efficient RAW Image Translation)
      • [MTRWKV: Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening](#MTRWKV: Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening)
      • [Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening](#Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening)
      • [POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP](#POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP)
      • [PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts](#PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts)
      • [Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening](#Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening)
      • [RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward](#RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward)
      • [Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery](#Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery)
      • [Seeing Through Blur: Tackling Defocus in Spike-Based Imaging](#Seeing Through Blur: Tackling Defocus in Spike-Based Imaging)
      • [Spatial-Spectral Residuals Informed Diffusion Neural Operator for Pan-sharpening](#Spatial-Spectral Residuals Informed Diffusion Neural Operator for Pan-sharpening)
      • [SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras](#SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras)
      • [Stability and Non-Local Modeling in Hybrid Convolution-Transformer Networks for Snapshot Hyperspectral Reconstruction](#Stability and Non-Local Modeling in Hybrid Convolution-Transformer Networks for Snapshot Hyperspectral Reconstruction)
      • [Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework](#Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework)
      • [Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis](#Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis)
      • [UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision](#UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision)
      • [White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation](#White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation)

整理汇总下2026年底层视觉(Low-Level Vision)相关的论文和代码，括超分辨率，图像去雨，图像去雾，去模糊，去噪，图像恢复，图像增强，图像去摩尔纹，图像修复，图像质量评价，插帧，图像/视频压缩等任务，具体如下。

最新修改版本会首先更新在Github，欢迎star，fork和PR~

也欢迎对底层视觉任务感兴趣的朋友一块更新～

Github ：Awesome-CVPR2026-Low-Level-Vision

知乎 ：https://zhuanlan.zhihu.com/p/2011913167840764194

参考或转载请注明出处

CVPR2025官网：https://cvpr.thecvf.com/Conferences/2025

CVPR接收论文列表：https://cvpr.thecvf.com/Conferences/2025/AcceptedPapers

CVPR完整论文库：

开会时间：2025月6月11日-2025月6月15日

论文接收公布时间：2025年2月27日

【Contents】

  • 1.超分辨率(Super-Resolution)
  • [2.图像去雨(Image Deraining)](#2.图像去雨(Image Deraining))
  • [3.图像去雾(Image Dehazing)](#3.图像去雾(Image Dehazing))
  • 4.去模糊(Deblurring)
  • 5.去噪(Denoising)
  • [6.图像恢复(Image Restoration)](#6.图像恢复(Image Restoration))
  • [7.图像增强(Image Enhancement)](#7.图像增强(Image Enhancement))
  • 8.图像修复(Inpainting)
  • [9.高动态范围成像(HDR Imaging)](#9.高动态范围成像(HDR Imaging))
  • [10.图像质量评价(Image Quality Assessment)](#10.图像质量评价(Image Quality Assessment))
  • [11.插帧(Frame Interpolation)](#11.插帧(Frame Interpolation))
  • [12.视频/图像压缩(Video/Image Compression)](#12.视频/图像压缩(Video/Image Compression))
  • [13.压缩图像质量增强(Compressed Image Quality Enhancement)](#13.压缩图像质量增强(Compressed Image Quality Enhancement))
  • [14.图像去反光(Image Reflection Removal)](#14.图像去反光(Image Reflection Removal))
  • [15.图像去阴影(Image Shadow Removal)](#15.图像去阴影(Image Shadow Removal))
  • [16.图像上色(Image Colorization)](#16.图像上色(Image Colorization))
  • [17.图像和谐化(Image Harmonization)](#17.图像和谐化(Image Harmonization))
  • [18.视频稳相(Video Stabilization)](#18.视频稳相(Video Stabilization))
  • [19.图像融合(Image Fusion)](#19.图像融合(Image Fusion))
  • 20.其他任务(Others)

1.超分辨率(Super-Resolution)

xxx

  • Paper:
  • Code:

AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution

Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution

CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness

Compressed-Domain-Aware Online Video Super-Resolution

Disentangled Textual Priors for Diffusion-based Image Super-Resolution

DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution

DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution

Dual Graph Regularized Deep Unfolding Network for Guided Depth Map Super-resolution

DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution

DVAR: Dynamic Visual Autoregressive Modeling for Image Super-Resolution

Edge-aware Multimodal Residual Diffusion Model for Hyperspectral Image Super-resolution

Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation

Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning

FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution

FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution

GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution

Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution

HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution

IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution

IFCSR: Inference-Free Fidelity-Realism Control for One-Step Diffusion-based Real-World Image Super-Resolution

Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution

LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution

One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution

Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual Correction

Plug-and-Play Dynamic In-context Learning with Stochastic Regularization for Screen Content Image Super-Resolution

PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion

QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution

RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution

Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework

Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance

Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features

SAT: Selective Aggregation Transformer for Image Super-Resolution

Spectral Super-Resolution via Adversarial Unfolding and Data-Driven Spectrum Regularization

SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting

STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution

TextOVSR: Text-Guided Real-World Opera Video Super-Resolution

Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors

Time-Aware One Step Diffusion Network for Real-World Image Super-Resolution

Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution

TinySR: Shallow Diffusion Transformers for Real-World Image Super-Resolution

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset

TPTransformer: Tensor-Tensor Product Transformer for Hyperspectral Image Super-Resolution

TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution

UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution

VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment

VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution

VOSR: A Vision-Only Generative Model for Image Super-Resolution

2.图像去雨(Image Deraining)

UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization

Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy

3.图像去雾(Image Dehazing)

Bilevel Layer-Positioning LoRA for Real Image Dehazing

Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus

From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing

HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching

Inf-Dehaze: Beyond GPU Memory Constraints for Ultra-High-Resolution Image Dehazing

4.去模糊(Deblurring)

BluRef: Unsupervised Image Deblurring with Dense-Matching References

Event-based Motion Deblurring with Unpaired Data

Gyro-based Deep Video Deblurring

Motion-Aware Animatable Gaussian Avatars Deblurring

MSCD-GS: Motion-Separated Cooperative Deblurring Dynamic Reconstruction via Gaussian Splatting

MVSSM: Motion-aware Visual State Space Model for Efficient Video Deblurring

OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring

SelfHVD: Self-Supervised Handheld Video Deblurring

Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor

Unblur-SLAM: Dense Neural SLAM for Blurry Inputs

5.去噪(Denoising)

2-Shots in the Dark: Low-Light Denoising with Minimal Data Acquisition

Back to Basics: Let Denoising Generative Models Denoise

Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising

Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning

Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices

Learning to Translate Noise for Robust Image Denoising

LF-BVN: Blind-View Network for Self-Supervised Light Field Denoising

Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising

RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference

Routing on Demand: DSNet for Efficient Progressive Point Cloud Denoising

Statistical Characteristic-Guided Denoising for Rapid High-Resolution Transmission Electron Microscopy Imaging

TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Denoising

Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation

6.图像恢复(Image Restoration)

Benchmarking Endoscopic Surgical Image Restoration and Beyond

Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration

Beyond the Ground Truth: Enhanced Supervision for Image Restoration

Beyond the Static-World: Lifelong Learning for All-in-One Medical Image Restoration

Blockwise Divide-and-Aggregate for Image Restoration using Diffusion Priors

CARD: Correlation Aware Restoration with Diffusion

DEBIR: Dynamic Exposure Burst Image Restoration

Degradation-Consistent Test-Time Adaptation for All-in-One Image Restoration

DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping

EpiAgent: An Agent-Centric System for Ancient Inscription Restoration

Evolutionary Multi-Agent Collaboration for Real-World Video Face Restoration

Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration

FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration

FlowSteer: Conditioning Flow Field for Consistent Image Restoration

FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model

Gaussian Splatting-based Low-Rank Tensor Representation for Multi-Dimensional Image Recovery

gQIR: Generative Quanta Image Reconstruction

GSNR: Graph Smooth Null-Space Representation for Inverse Problems

HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration

How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices

Hybrid Agents for Image Restoration

LWTformer: A Detail-Aware, Learnable Wavelet-Transformer for Ancient Chinese Character Image Restoration

MMDIR: Multimodal Instruction-Driven Framework for Mixed-Degradation Document Image Restoration

NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration

Optical Tolerance-Compensated Diffusion Model for Image Restoration

PGDR-BambooSlips: Physics-Guided Multistep Deformation Reversal for Ancient Bamboo Slip Restoration

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration

RDBM: Residual Diffusion Bridge Model for Image Restoration

Residual Diffusion Bridge Model for Image Restoration

Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback

Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration

Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank

Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration

Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration

ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration

Surgical Image Restoration Benchmark

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement

UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration

UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration

UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration

VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration

ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models

7.图像增强(Image Enhancement)

Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement

Bi-Bridge: Bidirectional Diffusion Bridges for Low-Light Image Enhancement

BiEvLight: Bi-level Learning of Task-Aware Event Refinement for Low-Light Image Enhancement

CtrlISP: Rescuing Low-Light RAW Images via Controllable Neural ISP

EIC-LIE: Event-Illumination Collaborative Low-light Image Enhancement

Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset

IF-Bench: Benchmarking and Enhancing MLLMs for Infrared Images

Leveraging Multispectral Sensors for Color Correction in Mobile Cameras

MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior

Multinex: Lightweight Low-Light Image Enhancement via Multi-prior Retinex

NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness

PrismNet: Semantic-Aware Image Enhancement via Vision Transformer and Zero-Cost Gating

RodNet: Visual Pathway-Inspired Adaptive Sparse Network for Efficient Low-Light Image Enhancement

SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control

Towards Generalized Representations for Low-Light Understanding: When Signal Constancy Meets Semantic Enrichment

VSRELL: A Simple Baseline for Video Super-Resolution and Enhancement in Low-Light environment

8.图像修复(Inpainting)

Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting

DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos

EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing

From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition

GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space

HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images

InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting

LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors

MAGIC: Few-Shot Mask-Guided Anomaly Inpainting

Object-WIPER: Training-Free Object and Associated Effect Removal in Video

PHAC: Promptable Human Amodal Completion

Precise Object and Effect Removal with Adaptive Target-Aware Attention

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

9.高动态范围成像(HDR Imaging)

Beyond8Bits: Full HDR UGC Dataset

ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction

F²HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling

LRHDR: Learning Representation-enhanced HDR Video Reconstruction

Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments

Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events

10.图像质量评价(Image Quality Assessment)

A^3: Towards Advertising Aesthetic Assessment

ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding

Bridging the Perception Gap in Image Super-Resolution Evaluation

Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

FluoCLIP: Stain-Aware Focus Quality Assessment in Fluorescence Microscopy

Generalizable Video Quality Assessment via Weak-to-Strong Learning

HDR-VLM: HDR-Domain Adaptation of VLMs and Preference-Aligned Quality Assessment for HDR Video Color Grading

Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency

Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling

MDS-VQA: Model-Informed Data Selection for Video Quality Assessment

Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline

Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment

PR-IQA: Partial-Reference Image Quality Assessment for Diffusion Models

QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment

Rethinking Knowledge Transfer in Image Quality Assessment: A Perceptual Preference Structure Alignment Perspective

RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360° Image Quality Assessment

rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training

Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos

VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment

11.插帧(Frame Interpolation)

Anchoring and Rescaling Attention for Semantically Coherent Inbetweening

LDF-VFI: Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

One-Shot Flow, Any-Time Frame: A Bidirectional Warping Framework for Event-Based Video Frame Interpolation

Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

12.视频/图像压缩(Video/Image Compression)

Adaptive Learned Image Compression with Graph Neural Networks

Beyond Pixel Loss: Video-INRs Prefer Perceptual Optimization

  • Paper:
  • Code:

Block-based Learned Image Compression without Blocking Artifacts

CADC: Content Adaptive Diffusion-Based Generative Image Compression

CoD: A Diffusion Foundation Model for Image Compression

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

Distributed Image Compression with Multimodal Side Information at Extremely Low Bitrates

DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression

FreqSIC: Frequency-aware Stereo Image Compression with Bi-directional Checkerboard Context Model

Generative Neural Video Compression via Video Diffusion Prior

Generative Video Compression with One-Dimensional Latent Representation

Learned Image Compression via Sparse Attention and Adaptive Frequency

Low-Bitrate Video Compression through Semantic-Conditioned Diffusion

MambaSIC: Mamba-based Stereo Image Compression with Bi-directional Multi-reference Entropy Model

OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data

Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression

Perceptual Neural Video Compression with Color Separation and Rank Chain

Real-Time Neural Video Compression with Unified Intra and Inter Coding

Ultra-Fast Neural Video Compression

Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression

What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters

What Matters in Practical Learned Image Compression

13.压缩图像/视频质量增强(Compressed Image/Video Quality Enhancement)

14.图像去反光(Image Reflection Removal)

GenSIRR: Rectifying Latent Space for Generative Single-Image Reflection Removal

GFRRN: Explore the Gaps in Single Image Reflection Removal

LightRR: A Lightweight Network for Single Image Reflection Removal

Polarization State Tracing for Reflection Removal and Color-Consistent Reconstruction

Rectifying Latent Space for Generative Single-Image Reflection Removal

Reflection Separation from a Single Image via Joint Latent Diffusion

ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation

15.图像去阴影(Image Shadow Removal)

PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors

16.图像上色(Image Colorization)

ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization

SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation

Towards High-resolution and Disentangled Reference-based Sketch Colorization

17.图像和谐化(Image Harmonization)

HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition

HarmoVid: Relightful Video Portrait Harmonization

18.视频稳相(Video Stabilization)

LightStab: Unsupervised Online Video Stabilization with Classical Priors

No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors

StabiGS: Video Stabilization through Rendering-Aware Trajectory Optimization in 3DGS-Reconstructed Scenes

19.图像融合(Image Fusion)

Beyond Strict Pairing: Arbitrarily Paired Training for High-Performance Infrared and Visible Image Fusion

Bridging Human Evaluation to Infrared and Visible Image Fusion

Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion

Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios

Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization

FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration

More Than Meets the Eye: A Unified Image Fusion Framework via Semantic-Pixel Entropy Trade-off for Zero-Shot Generalization

Multi-Modal Image Fusion via Intervention-Stable Feature Learning

Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared

Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion

PhyFusion: Physics-Aware Infrared and Visible Image Fusion via Modality-Specific Physical Priors

ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling

RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion

UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation

VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration

20.其他任务(Others)

3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion

AceTone: Bridging Words and Colors for Conditional Image Grading

Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration

D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping

Dark3R: Learning Structure from Motion in the Dark

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models

Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark

FastGaMer: Efficient GainMap Learning for Practical Inverse Tone Mapping

Fast Kernel-Space Diffusion for Remote Sensing Pansharpening

HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter

High-Quality and Efficient Turbulence Mitigation with Events

InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space

It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

Language-Guided One-Step Diffusion Model for Nighttime Flare Removal

Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal

LRDUN: A Low-Rank Deep Unfolding Network for Efficient Spectral Compressive Imaging

MERIT: Multi-domain Efficient RAW Image Translation

MTRWKV: Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening

Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening

POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening

RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward

Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery

Seeing Through Blur: Tackling Defocus in Spike-Based Imaging

Spatial-Spectral Residuals Informed Diffusion Neural Operator for Pan-sharpening

SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras

Stability and Non-Local Modeling in Hybrid Convolution-Transformer Networks for Snapshot Hyperspectral Reconstruction

Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework

Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis

UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision

White-Balance First, Adjust Later: Cross-Camera Color Constancy via Vision-Language Evaluation

持续更新~

相关推荐
埃菲尔铁塔_CV算法3 小时前
基于扩张卷积与双分支参数调控的低光照图像增强算法完整研究与工程解析
人工智能·神经网络·算法·机器学习·计算机视觉
sali-tec3 小时前
C# 基于OpenCv的视觉工作流-章81-弯脚检测
图像处理·人工智能·opencv·算法·计算机视觉
彭祥.3 小时前
基于SQLite与face_recognition的人脸库管理
数据库·计算机视觉·sqlite
前端摸鱼匠4 小时前
YOLOv11 深入 Ultralytics 框架的源码目录，解析 ultralytics/cfg/models/11/ 下的模型配置文件，以及 ultralytics/nn/modules/下的模块
人工智能·yolo·目标检测·计算机视觉·目标跟踪
懷淰メ4 小时前
【AI加持】基于PyQt+YOLO+DeepSeek的结直肠息肉检测系统（详细介绍）
yolo·目标检测·计算机视觉·pyqt·ai加持·直肠息肉·结直肠
apcipot_rain5 小时前
计科八股20260602——YOLO、弱监督学习、nnu-net、SAM
人工智能·神经网络·yolo·计算机视觉
HyperAI超神经5 小时前
在线教程丨英伟达开源LocateAnything，3B模型可实现图像+视频的目标指向/开放词汇目标检测/指代表达定位/OCR文本定位等功能
人工智能·目标检测·计算机视觉·ocr·目标文本定位
搬砖者（视觉算法工程师）6 小时前
计算机视觉与计算摄影测量学第四讲图像直方图变换：从理论推导到均衡化技术的深度解析
人工智能·计算机视觉
懷淰メ18 小时前
【AI加持】基于PyQt+YOLO+DeepSeek的疟原虫检测系统（详细介绍）
人工智能·yolo·计算机视觉·pyqt·医疗·ai分析·疟原虫
热门推荐
01GitHub 镜像站点022026 年 AI 编程工具终极横评：Cursor vs Claude Code vs Copilot vs Windsurf03【AI】2026 年具身智能模型和世界模型总结04Codex 下载安装指南：Windows 和 macOS 官方版下载05【踩坑记录 | 第一篇】微软商店无法使用时，如何手动安装 OpenAI Codex？附`.msix`文件系统错误解决方法06裂开！ChatGPT 居然开始要手机号验证，附详细解决方法07CC-Switch 下载、安装与使用配置指南【2026.5.29】08CC-Switch & Claude 基于 Linux 服务器安装使用指南09Codex 桌面端更新后 Chrome 插件和 Computer Use 不可用，怎么排查和修复10Codex 接入 DeepSeek API 完整配置文档