NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge
This addresses the problem of image restoration in real-world scenarios for researchers and practitioners, but it is incremental as it builds on existing challenge frameworks.
The paper reviews the NTIRE 2024 RAIM challenge, which tackled image restoration in the wild by constructing a benchmark with real-world images and requiring participants to restore images from complex degradation, resulting in top-ranked methods improving state-of-the-art performance and gaining unanimous recognition from judges.
In this paper, we review the NTIRE 2024 challenge on Restore Any Image Model (RAIM) in the Wild. The RAIM challenge constructed a benchmark for image restoration in the wild, including real-world images with/without reference ground truth in various scenarios from real applications. The participants were required to restore the real-captured images from complex and unknown degradation, where generative perceptual quality and fidelity are desired in the restoration result. The challenge consisted of two tasks. Task one employed real referenced data pairs, where quantitative evaluation is available. Task two used unpaired images, and a comprehensive user study was conducted. The challenge attracted more than 200 registrations, where 39 of them submitted results with more than 400 submissions. Top-ranked methods improved the state-of-the-art restoration performance and obtained unanimous recognition from all 18 judges. The proposed datasets are available at https://drive.google.com/file/d/1DqbxUoiUqkAIkExu3jZAqoElr_nu1IXb/view?usp=sharing and the homepage of this challenge is at https://codalab.lisn.upsaclay.fr/competitions/17632.