This paper reviews the AIM 2025 (Advances in Image Manipulation) Low-Light RAW Video Denoising Challenge. The task is to develop methods that denoise low-light RAW video by exploiting temporal redundancy while operating under exposure-time limits imposed by frame rate and adapting to sensor-specific, signal-dependent noise. We introduce a new benchmark of 756 ten-frame sequences captured with 14 smartphone camera sensors across nine conditions (illumination: 1/5/10 lx; exposure: 1/24, 1/60, 1/120 s), with high-SNR references obtained via burst averaging. Participants process linear RAW sequences and output the denoised 10th frame while preserving the Bayer pattern. Submissions are evaluated on a private test set using full-reference PSNR and SSIM, with final ranking given by the mean of per-metric ranks. This report describes the dataset, challenge protocol, and submitted approaches.
@article{arxiv.2508.16830,
title = {AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results},
author = {Alexander Yakovenko and George Chakvetadze and Ilya Khrapov and Maksim Zhelezov and Dmitry Vatolin and Radu Timofte and Youngjin Oh and Junhyeong Kwon and Junyoung Park and Nam Ik Cho and Senyan Xu and Ruixuan Jiang and Long Peng and Xueyang Fu and Zheng-Jun Zha and Xiaoping Peng and Hansen Feng and Zhanyi Tie and Ziming Xia and Lizhi Wang},
journal= {arXiv preprint arXiv:2508.16830},
year = {2025}
}
Comments
Challenge report from Advances in Image Manipulation workshop held at ICCV 2025