Signals 4 · free daily AI digest

Benchmarking RAW and RGB Restoration in Image Signal Processors

Paper recorded by Signals 4 on 2026-09-02 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-02 on arXiv · recorded by Signals 4 on 2026-09-03

Category: cs.CV · 计算机视觉 · first seen 2026-09-03

Abstract

Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A) pre-ISP restoration in the RAW domain and (B) post-ISP restoration in the sRGB domain. The benchmark covers four smartphone device groups, two learned ISPs, three degradation regimes--noise, blur, and joint noise and bl

Read on arXiv →

#164 most recent of 237 cs.CV papers we have recorded · ↑ newer: Efficient All-in-One Weather Restoration using Spectral Harmonization · ↓ older: GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic De
Cite this page: Benchmarking RAW and RGB Restoration in Image Signal Processors: the #164 most recent of 237 cs.CV papers we have recorded (as of 2026-09-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/benchmarking-raw-and-rgb-restoration-in-image-signal-processors.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions