arXiv · 2611.19284
LC-ISP Benchmark: Learning Advanced ISP with Live and Capture Streams
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$\times$448 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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Kai Chen, Junyu Lou, Jinhua Zhang, Weiyi You, Shuhang Gu. 2026-11-14. LC-ISP Benchmark: Learning Advanced ISP with Live and Capture Streams. https://searcharxiv.com/abs/2611.19284
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.