AIM 2025 Challenge on Real-World RAW Image Denoising
This addresses the problem of low-light image denoising for applications in digital photography and autonomous driving, but it is incremental as it builds upon existing competition frameworks.
The paper introduced the AIM 2025 Challenge to advance real-world RAW image denoising by creating a benchmark with low-light noisy images from five DSLR cameras, where participants developed methods to achieve high performance across camera models based on metrics like PSNR and SSIM.
We introduce the AIM 2025 Real-World RAW Image Denoising Challenge, aiming to advance efficient and effective denoising techniques grounded in data synthesis. The competition is built upon a newly established evaluation benchmark featuring challenging low-light noisy images captured in the wild using five different DSLR cameras. Participants are tasked with developing novel noise synthesis pipelines, network architectures, and training methodologies to achieve high performance across different camera models. Winners are determined based on a combination of performance metrics, including full-reference measures (PSNR, SSIM, LPIPS), and non-reference ones (ARNIQA, TOPIQ). By pushing the boundaries of camera-agnostic low-light RAW image denoising trained on synthetic data, the competition promotes the development of robust and practical models aligned with the rapid progress in digital photography. We expect the competition outcomes to influence multiple domains, from image restoration to night-time autonomous driving.