NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge

TL;DR

The NTIRE 2024 RAIM challenge introduced a new benchmark for real-world image restoration, emphasizing perceptual quality and fidelity in complex, unknown degradations, with top methods surpassing previous state-of-the-art results.

Contribution

This paper presents a new benchmark dataset and challenge framework for real-world image restoration, highlighting the latest advancements in handling complex degradations.

Findings

Top methods improved state-of-the-art restoration performance.

The challenge attracted over 200 participants and 400 submissions.

Unanimous recognition from judges for top methods.

Abstract

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.