PaperScope
LIVE · 2026-09-17 05:40 UTC

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

Tailai Chen, Xiaotong Luo, Yuan Gao, Xin Jin, Wenjun Zeng

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.18302 v1
Submitted
2026-09-16

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.

Comment: Accepted at ECCV 2026 Workshop on Low-Level Vision Frontiers (LoViF). 13 pages, 4 figures

arXiv abs page · PDF · same-day batch