cs.CVNov 14, 2026

LC-ISP Benchmark: Learning Advanced ISP with Live and Capture Streams

Authors: Kai Chen, Junyu Lou, Jinhua Zhang, Weiyi You, Shuhang Gu

Organizations: University of Electronic Science and Technology of China

Abstract

High-quality paired RAW-to-sRGB datasets are essential for data-driven ISP, yet existing datasets often rely on cross-device collection, causing misalignment and failing to faithfully reflect real capture conditions. We therefore introduce LC-ISP, a large-scale benchmark built from the intrinsic gap between a camera's live preview and offline capture streams. LC-ISP contains 53.9k spatially aligned groups, each comprising live RAW/live sRGB and multi-frame fused RGB/capture sRGB, and covers day, night, indoor, outdoor, and HDR scenes. It also provides capture-stream intermediates for modular supervision. We further develop a compact two-stage baseline that uses these intermediates as auxiliary targets. Under a 2.5-GFLOP budget for 448×\times448 RAW inputs, it outperforms the strongest single-frame baseline by over 2 dB PSNR while improving texture, denoising, and color reproduction. LC-ISP supports realistic benchmarking, the design of supervision strategies, and the development of lightweight ISP models.

Figures & tables

Explore similar work

CardsList
  1. RawGen: Learning Camera Raw Image Generation

    Mar 31, 2026Dongyoung Kim, Junyong Lee, Abhijith Punnappurath +4Computational ImagingImage Generation

  2. A Reference-Free Framework for Evaluating Single-Frame ISP Pipelines

    Jul 25, 2026Yujin Cho, Sira Ferradans, Jean-Michel Morel +2Image Quality Assessment

  3. R3\mathbf{R}^3: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain

    Sep 28, 2025Nate Rothschild, Moshe Kimhi, Avi Mendelson +1Image DerainingImage Restoration