一种用于评估单帧 ISP 管道的无参考框架
A Reference-Free Framework for Evaluating Single-Frame ISP Pipelines
浏览论文内容
中文总结 AI 辅助
该研究针对相机 ISP 管道评估难题，提出无参考学习框架，从处理后的 sRGB 图像及其 ISO 元数据估计全参考图像质量指标，经实验验证其可行性，在估计指标值上优于直接度量回归，与全参考排名一致性更高。
中文摘要 AI 辅助
评估相机图像信号处理（ISP）管道需要测量去噪、去马赛克、色调映射和压缩等操作引入的低级伪像。盲图像质量评估（IQA）技术可在无参考情况下对视觉质量进行评分，但通常关注语义和高级视觉线索或人类感知分数，而非相机管道引入的低级图像处理伪像。相比之下，诸如 PSNR 和 SSIM 等全参考指标测量像素级差异和结构相似性，LPIPS 测量深度特征空间中的感知相似性。然而，这些指标需要完美对齐的图像对，在实际设置中难以收集。我们提出一种无参考学习框架，从处理后的 sRGB 图像及其 ISO 元数据估计全参考图像质量指标。我们的方法预测一个代理 sRGB 参考，然后将其与处理后的图像进行比较，以计算标准全参考形式的 PSNR、SSIM 和 LPIPS。我们的实验表明，代理参考模型可以从合成数据中学习并应用于真实相机数据。我们进一步表明，轻量级 LoRA微调在 ISP 组件或管道配置改变时能实现高效适应。所提出方法在估计指标值方面优于直接度量回归，并且与传统盲 IQA 方法相比，与全参考排名的一致性更高。这些结果证明了无参考估计全参考指标用于实际相机管道评估的可行性。
英文摘要
Evaluating camera image signal processing (ISP) pipelines requires measuring low-level artifacts introduced by operations such as denoising, demosaicing, tone mapping, and compression. Blind image quality assessment (IQA) techniques can grade visual quality without a reference, but they typically focus on semantic and high-level visual cues or human perceptual scores rather than the low-level image-processing artifacts introduced by camera pipelines. In contrast, full-reference metrics such as PSNR and SSIM measure pixel-level differences and structural similarity, while LPIPS measures perceptual similarity in deep feature space. However, these metrics require perfectly aligned image pairs, which are difficult to collect in practical settings. We propose a reference-free learning framework that estimates full-reference image quality metrics from a processed sRGB image and its ISO metadata. Our method predicts a proxy sRGB reference, which is then compared with the processed image to compute PSNR, SSIM, and LPIPS in their standard full-reference form. Our experiments show that the proxy-reference model can be learned from synthetic data and applied to real camera data. We further show that lightweight LoRA fine-tuning enables efficient adaptation when ISP components or pipeline configurations are changed. The proposed method outperforms direct metric regression in estimating metric values and achieves higher agreement with full-reference rankings than conventional blind IQA methods. These results demonstrate the feasibility of reference-free estimation of full-reference metrics for practical camera-pipeline evaluation.
发表机构
- ENS Paris-Saclay（巴黎-萨克兰高等师范学院）
- DXOMARK（DXOMARK公司）
- Lingnan University（岭南大学）
- CFM（CFM机构）
- Institut Universitaire de France（法国大学研究院）
机构由 AI 辅助整理，请以论文原文为准。
