视觉自回归先验用于RAW到sRGB图像信号处理
Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
- OmniVision-IDT Joint Laboratory for Intelligent Image Sensing（豪威科技-东方理工智能图像感知联合实验室）
- Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波市空间智能与数字衍生重点实验室）
- Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo（宁波东方理工数字孪生研究院）
- Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin（浙江省工业智能与数字孪生重点实验室）
- The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文首次将视觉自回归先验用于RAW到sRGB ISP，仅微调2.99%参数，通过频率分解颜色损失在Zurich基准上提升PSNR-Y 0.58dB、降低LPIPS 0.058，并指出颜色转移是主要瓶颈。
AI中文摘要：
RAW到sRGB图像信号处理（ISP）必须从传感器测量中恢复感知上忠实的颜色和精细细节，通常面临空间对齐不完美和相机元数据缺失的情况。本文提出了，据我们所知，首次将视觉自回归（VAR）下一尺度预测应用于离散图像码本上的RAW到sRGB ISP任务。我们适配了一个冻结的1.10B参数VAR主干用于RAW条件ISP，仅需32.93M可训练参数（2.99%），并提出了频率分解颜色损失，通过小波LL余弦相似度单独监督低频色调，通过细节带$\ell_1$监督彩色边缘。在Zurich RAW到sRGB基准上，该方法在完整1,204图像测试集上将PSNR-Y从21.31提高到21.89 dB，并将LPIPS从0.276降低到0.218。诊断实验表明，VAR先验能很好地保持结构，但连续颜色转移仍是主要瓶颈：oracle仿射校正恢复了3.8 dB，而学习到的颜色头仅带来微小增益。
英文摘要：
RAW-to-sRGB image signal processing (ISP) must recover perceptually faithful colors and fine details from sensor measurements, often under imperfect spatial alignment and missing camera metadata. This paper presents, to the best of our knowledge, the first application of visual autoregressive (VAR) next-scale prediction over a discrete image codebook to the RAW-to-sRGB ISP task. We adapt a frozen 1.10\,B-parameter VAR backbone for RAW-conditioned ISP with only 32.93\,M trainable parameters (2.99\%), and propose a frequency-decomposed color loss that separately supervises low-frequency tone via wavelet LL cosine similarity and chromatic edges via detail-band $\ell_1$. On the Zurich RAW-to-sRGB benchmark, the method improves PSNR-Y from 21.31 to 21.89\,dB and reduces LPIPS from 0.276 to 0.218 on the full 1,204-image test set. Diagnostic experiments show that the VAR prior preserves structure well, but continuous color transfer remains the dominant bottleneck: oracle affine correction recovers 3.8\,dB, while learned color heads yield marginal gains.
