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

arXiv:2609.18302v1 Announce Type: new 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.

Related

• Benchmarking RAW and RGB Restoration in Image Signal Processors
• sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
• Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors

Source: arXiv cs.CV | 2026-09-17