C# OnnxRuntime 部署 RMBG-2.0 实现高精度背景去除

目录

说明

[RMBG-2.0 是什么](#RMBG-2.0 是什么)

[BiRefNet 架构的核心思想](#BiRefNet 架构的核心思想)

效果

模型信息

项目

代码

下载

模型下载


说明

背景去除是图像处理中的一个经典难题。从早期的颜色键控、GrabCut,到如今基于深度学习的分割模型,技术的演进让抠图这件事变得越来越智能。而在众多背景去除方案中,BRIA AI 开源的 RMBG-2.0 凭借其极高的精度和良好的工程化能力,成为当前这一领域备受关注的选择。

本文将介绍如何在 C# 中使用 ONNX Runtime 部署 RMBG-2.0 模型,实现高精度的图像背景去除,输出带透明通道的 PNG 图片。全文包含完整的代码实现,适合希望将 AI 抠图能力集成到 .NET 应用中的开发者参考。

RMBG-2.0 是什么

RMBG-2.0(Remove Background 2.0)是 BRIA AI 推出的新一代图像背景移除模型,基于 BiRefNet(Bilateral Reference Network,双边参考网络)架构设计。相比前代 RMBG v1.4,准确率从 73.94% 大幅提升至 90.14%,超越了不少商业付费工具

BiRefNet 架构的核心思想

传统图像分割模型往往把任务简化为"给每个像素打标签"------是前景就是 1,是背景就是 0。这种单向分类思维在处理发丝、纱巾、玻璃反光等边界模糊区域时,天然存在歧义。

BiRefNet 换了一种思路:它不直接预测分割图,而是构建一个双向参考系统------前景参考分支聚焦于主体内部结构,背景参考分支同步分析周围环境,两个分支在特征空间进行交叉调制,共同完成高保真分割。

具体来说,BiRefNet 由两个核心模块构成:定位模块(Localization Module, LM) 负责理解全局语义、生成语义图;恢复模块(Restoration Module, RM) 负责边缘细节的精修,通过边缘感知注意力机制实现对发丝级细节的精细处理。

这种设计使得 RMBG-2.0 在保持计算效率的同时,能够精准处理复杂边缘。

效果

模型信息

Model Properties



Inputs


name:pixel_values

tensor:Float[1, 3, -1, -1]


Outputs


name:alphas

tensor:Float[1, 1, -1, -1]


项目

代码

using Microsoft.ML.OnnxRuntime;

using Microsoft.ML.OnnxRuntime.Tensors;

using OpenCvSharp;

using System;

using System.Collections.Generic;

using System.Drawing;

using System.Drawing.Imaging;

using System.Linq;

using System.Windows.Forms;

namespace Onnx_Demo

{

public partial class Form1 : Form

{

public Form1()

{

InitializeComponent();

}

string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";

string image_path = "";

string startupPath;

DateTime dt1 = DateTime.Now;

DateTime dt2 = DateTime.Now;

string model_path;

Mat image; // 原始图像(BGR)

Mat result_image_with_alpha; // 最终带有透明背景的图像

SessionOptions options;

InferenceSession onnx_session;

Tensor<float> input_tensor;

List<NamedOnnxValue> input_container;

IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;

int inpHeight, inpWidth;

// RMBG-2.0 预处理参数

private readonly float[] mean = new float[] { 0.485f, 0.456f, 0.406f };

private readonly float[] std = new float[] { 0.229f, 0.224f, 0.225f };

private void button1_Click(object sender, EventArgs e)

{

OpenFileDialog ofd = new OpenFileDialog();

ofd.Filter = fileFilter;

if (ofd.ShowDialog() != DialogResult.OK) return;

pictureBox1.Image = null;

image_path = ofd.FileName;

pictureBox1.Image = new Bitmap(image_path);

textBox1.Text = "";

image = new Mat(image_path);

pictureBox2.Image = null;

}

private void button2_Click(object sender, EventArgs e)

{

if (image_path == "")

{

return;

}

button2.Enabled = false;

pictureBox2.Image = null;

textBox1.Text = "";

Application.DoEvents();

// 读取原始图像(BGR)

image = new Mat(image_path);

int originalWidth = image.Cols;

int originalHeight = image.Rows;

// ------------------ 预处理 ------------------

// 1. 转换为RGB

Mat rgb = new Mat();

Cv2.CvtColor(image, rgb, ColorConversionCodes.BGR2RGB);

// 2. Resize到模型输入尺寸(1024x1024)

Mat resized = new Mat();

Cv2.Resize(rgb, resized, new OpenCvSharp.Size(inpWidth, inpHeight));

// 3. 转换为浮点并归一化到 [0,1]

resized.ConvertTo(resized, MatType.CV_32FC3, 1.0 / 255.0);

// 4. 分离通道并应用标准化 (value - mean) / std

Mat[] channels = Cv2.Split(resized); // R, G, B

float[] inputData = new float[3 * inpHeight * inpWidth];

int channelSize = inpHeight * inpWidth;

for (int c = 0; c < 3; c++)

{

float[] channelData = new float[channelSize];

System.Runtime.InteropServices.Marshal.Copy(channels[c].Data, channelData, 0, channelSize);

// 标准化每个通道

for (int i = 0; i < channelSize; i++)

{

channelData[i] = (channelData[i] - mean[c]) / std[c];

}

Array.Copy(channelData, 0, inputData, c * channelSize, channelSize);

}

// 创建输入张量 (1, 3, H, W)

input_tensor = new DenseTensor<float>(inputData, new[] { 1, 3, inpHeight, inpWidth });

// 将输入放入容器(使用正确的输入名称 pixel_values)

input_container.Clear();

input_container.Add(NamedOnnxValue.CreateFromTensor("pixel_values", input_tensor));

// ------------------ 推理 ------------------

dt1 = DateTime.Now;

result_infer = onnx_session.Run(input_container);

dt2 = DateTime.Now;

// 按输出名称 alphas 获取结果

var output = result_infer.First(x => x.Name == "alphas").AsTensor<float>();

int[] outShape = output.Dimensions.ToArray();

int outH = outShape[2];

int outW = outShape[3];

float[] predFloat = output.ToArray().Select(x => (float)x).ToArray();

// 创建单通道 Mat(Alpha 蒙版,值域 [0,1])

Mat alphaMat = new Mat(outH, outW, MatType.CV_32FC1, predFloat);

// ------------------ 后处理 ------------------

// 1. 双线性插值到原始尺寸

Mat maskResized = new Mat();

Cv2.Resize(alphaMat, maskResized, new OpenCvSharp.Size(originalWidth, originalHeight), interpolation: InterpolationFlags.Linear);

// 2. 确保值在 [0,1] 范围内(sigmoid输出理论如此,防止溢出)

Cv2.Threshold(maskResized, maskResized, 1.0, 1.0, ThresholdTypes.Trunc);

Cv2.Threshold(maskResized, maskResized, 0.0, 0.0, ThresholdTypes.Tozero);

// 3. 转换为8位单通道(alpha 0~255)

Mat alphaMask = new Mat();

maskResized.ConvertTo(alphaMask, MatType.CV_8UC1, 255.0);

// ------------------ 合成透明背景图像 ------------------

// 原始图像(BGR)转为 BGRA

Mat rgba = new Mat();

Cv2.CvtColor(image, rgba, ColorConversionCodes.BGR2BGRA);

// 替换 alpha 通道

Mat[] bgraChannels = Cv2.Split(rgba);

bgraChannels[3] = alphaMask;

Cv2.Merge(bgraChannels, rgba);

result_image_with_alpha = rgba.Clone();

// 显示最终图像(PictureBox 支持透明通道显示)

pictureBox2.Image = new Bitmap(rgba.ToMemoryStream());

textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";

button2.Enabled = true;

}

private void Form1_Load(object sender, EventArgs e)

{

startupPath = System.Windows.Forms.Application.StartupPath;

model_path = "model/model.onnx"; // 请确保模型文件存在于此路径

// 创建会话,使用 CPU(可根据需要改为 CUDA)

options = new SessionOptions();

options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;

options.AppendExecutionProvider_CPU(0);

onnx_session = new InferenceSession(model_path, options);

input_container = new List<NamedOnnxValue>();

// 模型固定输入尺寸

inpHeight = 1024;

inpWidth = 1024;

// 测试图片路径(可选)

image_path = "test_img/1.jpg";

if (System.IO.File.Exists(image_path))

{

pictureBox1.Image = new Bitmap(image_path);

image = new Mat(image_path);

}

}

private void pictureBox1_DoubleClick(object sender, EventArgs e)

{

Common.ShowNormalImg(pictureBox1.Image);

}

private void pictureBox2_DoubleClick(object sender, EventArgs e)

{

Common.ShowNormalImg(pictureBox2.Image);

}

SaveFileDialog sdf = new SaveFileDialog();

private void button3_Click(object sender, EventArgs e)

{

if (result_image_with_alpha == null || result_image_with_alpha.Empty())

{

MessageBox.Show("请先进行推理!");

return;

}

sdf.Title = "保存透明背景图片";

sdf.Filter = "PNG图片 (*.png)|*.png|JPEG图片 (*.jpg)|*.jpg|BMP图片 (*.bmp)|*.bmp";

sdf.FilterIndex = 1; // 默认 PNG,保留透明度

if (sdf.ShowDialog() == DialogResult.OK)

{

string ext = System.IO.Path.GetExtension(sdf.FileName).ToLower();

ImageFormat format = ImageFormat.Png;

if (ext == ".jpg" || ext == ".jpeg")

format = ImageFormat.Jpeg;

else if (ext == ".bmp")

format = ImageFormat.Bmp;

using (var stream = result_image_with_alpha.ToMemoryStream())

using (var bitmap = new Bitmap(stream))

{

bitmap.Save(sdf.FileName, format);

}

MessageBox.Show("保存成功,位置:" + sdf.FileName);

}

}

}

}

复制代码
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using OpenCvSharp;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.Linq;
using System.Windows.Forms;

namespace Onnx_Demo
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }

        string fileFilter = "*.*|*.bmp;*.jpg;*.jpeg;*.tiff;*.tiff;*.png";
        string image_path = "";
        string startupPath;
        DateTime dt1 = DateTime.Now;
        DateTime dt2 = DateTime.Now;
        string model_path;
        Mat image;                       // 原始图像(BGR)
        Mat result_image_with_alpha;     // 最终带有透明背景的图像
        SessionOptions options;
        InferenceSession onnx_session;
        Tensor<float> input_tensor;
        List<NamedOnnxValue> input_container;
        IDisposableReadOnlyCollection<DisposableNamedOnnxValue> result_infer;
        int inpHeight, inpWidth;

        // RMBG-2.0 预处理参数
        private readonly float[] mean = new float[] { 0.485f, 0.456f, 0.406f };
        private readonly float[] std = new float[] { 0.229f, 0.224f, 0.225f };

        private void button1_Click(object sender, EventArgs e)
        {
            OpenFileDialog ofd = new OpenFileDialog();
            ofd.Filter = fileFilter;
            if (ofd.ShowDialog() != DialogResult.OK) return;
            pictureBox1.Image = null;
            image_path = ofd.FileName;
            pictureBox1.Image = new Bitmap(image_path);
            textBox1.Text = "";
            image = new Mat(image_path);
            pictureBox2.Image = null;
        }

        private void button2_Click(object sender, EventArgs e)
        {
            if (image_path == "")
            {
                return;
            }

            button2.Enabled = false;
            pictureBox2.Image = null;
            textBox1.Text = "";
            Application.DoEvents();

            // 读取原始图像(BGR)
            image = new Mat(image_path);
            int originalWidth = image.Cols;
            int originalHeight = image.Rows;

            // ------------------ 预处理 ------------------
            // 1. 转换为RGB
            Mat rgb = new Mat();
            Cv2.CvtColor(image, rgb, ColorConversionCodes.BGR2RGB);

            // 2. Resize到模型输入尺寸(1024x1024)
            Mat resized = new Mat();
            Cv2.Resize(rgb, resized, new OpenCvSharp.Size(inpWidth, inpHeight));

            // 3. 转换为浮点并归一化到 [0,1]
            resized.ConvertTo(resized, MatType.CV_32FC3, 1.0 / 255.0);

            // 4. 分离通道并应用标准化 (value - mean) / std
            Mat[] channels = Cv2.Split(resized);   // R, G, B
            float[] inputData = new float[3 * inpHeight * inpWidth];
            int channelSize = inpHeight * inpWidth;

            for (int c = 0; c < 3; c++)
            {
                float[] channelData = new float[channelSize];
                System.Runtime.InteropServices.Marshal.Copy(channels[c].Data, channelData, 0, channelSize);

                // 标准化每个通道
                for (int i = 0; i < channelSize; i++)
                {
                    channelData[i] = (channelData[i] - mean[c]) / std[c];
                }

                Array.Copy(channelData, 0, inputData, c * channelSize, channelSize);
            }

            // 创建输入张量 (1, 3, H, W)
            input_tensor = new DenseTensor<float>(inputData, new[] { 1, 3, inpHeight, inpWidth });

            // 将输入放入容器(使用正确的输入名称 pixel_values)
            input_container.Clear();
            input_container.Add(NamedOnnxValue.CreateFromTensor("pixel_values", input_tensor));

            // ------------------ 推理 ------------------
            dt1 = DateTime.Now;
            result_infer = onnx_session.Run(input_container);
            dt2 = DateTime.Now;

            // 按输出名称 alphas 获取结果
            var output = result_infer.First(x => x.Name == "alphas").AsTensor<float>();
            int[] outShape = output.Dimensions.ToArray();
            int outH = outShape[2];
            int outW = outShape[3];

            float[] predFloat = output.ToArray().Select(x => (float)x).ToArray();

            // 创建单通道 Mat(Alpha 蒙版,值域 [0,1])
            Mat alphaMat = new Mat(outH, outW, MatType.CV_32FC1, predFloat);

            // ------------------ 后处理 ------------------
            // 1. 双线性插值到原始尺寸
            Mat maskResized = new Mat();
            Cv2.Resize(alphaMat, maskResized, new OpenCvSharp.Size(originalWidth, originalHeight), interpolation: InterpolationFlags.Linear);

            // 2. 确保值在 [0,1] 范围内(sigmoid输出理论如此,防止溢出)
            Cv2.Threshold(maskResized, maskResized, 1.0, 1.0, ThresholdTypes.Trunc);
            Cv2.Threshold(maskResized, maskResized, 0.0, 0.0, ThresholdTypes.Tozero);

            // 3. 转换为8位单通道(alpha 0~255)
            Mat alphaMask = new Mat();
            maskResized.ConvertTo(alphaMask, MatType.CV_8UC1, 255.0);

            // ------------------ 合成透明背景图像 ------------------
            // 原始图像(BGR)转为 BGRA
            Mat rgba = new Mat();
            Cv2.CvtColor(image, rgba, ColorConversionCodes.BGR2BGRA);

            // 替换 alpha 通道
            Mat[] bgraChannels = Cv2.Split(rgba);
            bgraChannels[3] = alphaMask;
            Cv2.Merge(bgraChannels, rgba);

            result_image_with_alpha = rgba.Clone();

            // 显示最终图像(PictureBox 支持透明通道显示)
            pictureBox2.Image = new Bitmap(rgba.ToMemoryStream());

            textBox1.Text = "推理耗时:" + (dt2 - dt1).TotalMilliseconds + "ms";
            button2.Enabled = true;
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            startupPath = System.Windows.Forms.Application.StartupPath;
            model_path = "model/model.onnx";   // 请确保模型文件存在于此路径

            // 创建会话,使用 CPU(可根据需要改为 CUDA)
            options = new SessionOptions();
            options.LogSeverityLevel = OrtLoggingLevel.ORT_LOGGING_LEVEL_INFO;
            options.AppendExecutionProvider_CPU(0);

            onnx_session = new InferenceSession(model_path, options);
            input_container = new List<NamedOnnxValue>();

            // 模型固定输入尺寸
            inpHeight = 1024;
            inpWidth = 1024;

            // 测试图片路径(可选)
            image_path = "test_img/1.jpg";
            if (System.IO.File.Exists(image_path))
            {
                pictureBox1.Image = new Bitmap(image_path);
                image = new Mat(image_path);
            }
        }

        private void pictureBox1_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox1.Image);
        }

        private void pictureBox2_DoubleClick(object sender, EventArgs e)
        {
            Common.ShowNormalImg(pictureBox2.Image);
        }

        SaveFileDialog sdf = new SaveFileDialog();
        private void button3_Click(object sender, EventArgs e)
        {
            if (result_image_with_alpha == null || result_image_with_alpha.Empty())
            {
                MessageBox.Show("请先进行推理!");
                return;
            }

            sdf.Title = "保存透明背景图片";
            sdf.Filter = "PNG图片 (*.png)|*.png|JPEG图片 (*.jpg)|*.jpg|BMP图片 (*.bmp)|*.bmp";
            sdf.FilterIndex = 1;   // 默认 PNG,保留透明度
            if (sdf.ShowDialog() == DialogResult.OK)
            {
                string ext = System.IO.Path.GetExtension(sdf.FileName).ToLower();
                ImageFormat format = ImageFormat.Png;
                if (ext == ".jpg" || ext == ".jpeg")
                    format = ImageFormat.Jpeg;
                else if (ext == ".bmp")
                    format = ImageFormat.Bmp;

                using (var stream = result_image_with_alpha.ToMemoryStream())
                using (var bitmap = new Bitmap(stream))
                {
                    bitmap.Save(sdf.FileName, format);
                }
                MessageBox.Show("保存成功,位置:" + sdf.FileName);
            }
        }
    }
}

下载

源码下载

模型下载

通过网盘分享的文件:RMBG-2.0 模型

链接: https://pan.baidu.com/s/12pA3YBoDQqVEEO-PkDBg8w?pwd=tqj7 提取码: tqj7

相关推荐
wei_shuo2 年前
Modnet 人像抠图(论文复现)
人像抠图
知来者逆2 年前
人像抠图HumanSeg——基于大规模电话会议视频数据集的连接感知人像分割
深度学习·图像分割·人像分割·抠图·paddleseg·人像抠图·一键抠图