AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results

TL;DR

This paper presents the AIM 2025 Low-Light RAW Video Denoising Challenge, introducing a new dataset, evaluation protocol, and analyzing various methods for denoising low-light RAW videos under realistic constraints.

Contribution

It introduces a comprehensive benchmark dataset, challenge protocol, and evaluation framework for low-light RAW video denoising, fostering progress in this specialized area.

Findings

New dataset with 756 sequences across 14 sensors and 9 conditions.

Evaluation of multiple denoising approaches using PSNR and SSIM.

Benchmark results highlight current state-of-the-art performance and challenges.

Abstract

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.