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

arXiv: https://arxiv.org/abs/2609.18302 · HTML: https://mlsanity.com/paper/2609.18302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [AIM 2020 Challenge on Learned Image Signal Processing Pipeline](https://mlsanity.com/paper/2011.04994/) (2020)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [AWNet: Attentive Wavelet Network for Image ISP](https://mlsanity.com/paper/2008.09228/) (2020)
- [Visual Autoregressive Modeling for Image Super-Resolution](https://mlsanity.com/paper/2501.18993/) (2025)
- [Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07809/) (2021)
- [RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.18047/) (2025)
- [Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain](https://mlsanity.com/paper/2401.02161/) (2024)
- [W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping](https://mlsanity.com/paper/1911.08656/) (2019)
- [ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistency](https://mlsanity.com/paper/2503.19283/) (2025)
- [RMFA-Net: A Neural ISP for Real RAW to RGB Image Reconstruction](https://mlsanity.com/paper/2406.11469/) (2024)

## Abstract (arXiv)

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 ℓ1. 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.