This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This manuscript focuses on the competition set-up, the proposed methods and their respective results. The challenge aims at producing novel camera view synthesis of diverse scenes from sparse image observations. It is composed of two tracks, with differing levels of sparsity; 3 views in Track 1 (very sparse) and 9 views in Track 2 (sparse). Participants are asked to optimise objective fidelity to the ground-truth images as measured via the Peak Signal-to-Noise Ratio (PSNR) metric. For both tracks, we use the newly introduced Sparse Rendering (SpaRe) dataset and the popular DTU MVS dataset. In this challenge, 5 teams submitted final results to Track 1 and 4 teams submitted final results to Track 2. The submitted models are varied and push the boundaries of the current state-of-the-art in sparse neural rendering. A detailed description of all models developed in the challenge is provided in this paper.
@article{arxiv.2409.15045,
title = {AIM 2024 Sparse Neural Rendering Challenge: Methods and Results},
author = {Michal Nazarczuk and Sibi Catley-Chandar and Thomas Tanay and Richard Shaw and Eduardo Pérez-Pellitero and Radu Timofte and Xing Yan and Pan Wang and Yali Guo and Yongxin Wu and Youcheng Cai and Yanan Yang and Junting Li and Yanghong Zhou and P. Y. Mok and Zongqi He and Zhe Xiao and Kin-Chung Chan and Hana Lebeta Goshu and Cuixin Yang and Rongkang Dong and Jun Xiao and Kin-Man Lam and Jiayao Hao and Qiong Gao and Yanyan Zu and Junpei Zhang and Licheng Jiao and Xu Liu and Kuldeep Purohit},
journal= {arXiv preprint arXiv:2409.15045},
year = {2024}
}
Comments
Part of Advances in Image Manipulation workshop at ECCV 2024