Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing

2026-09-16

AI Summary

本文使用视觉自回归模型处理RAW-to-sRGB图像信号，通过频率分解色彩损失优化，以恢复感知上忠实的颜色和细节。

Abstract

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.

Problem

• RAW-to-sRGB
• Image Signal Processing
• Spatial Alignment
• Camera Metadata

Innovation

• visual autoregressive
• next-scale prediction
• discrete image codebook
• frequency-decomposed color loss
• RAW-to-sRGB ISP