评测稀疏神经渲染新方法，5支团队在3视角下突破性能极限
AIM 2024 Sparse Neural Rendering Challenge: Methods and Results
- 设计双轨挑战：3视图（极稀疏）与9视图（稀疏）场景重建
- 使用SpaRe和DTU MVS数据集，最高PSNR达38.6（Track 1）
- 展示多种创新架构，适合研究稀疏视图合成的开发者参考
本文回顾了2024年欧洲计算机视觉大会（ECCV 2024）期间举办的图像操控前沿研讨会（AIM）中关于稀疏神经渲染的挑战。该挑战旨在从稀疏图像观测中生成新视角的高质量图像，分为两个赛道：第1赛道仅提供3个视图（极稀疏），第2赛道提供9个视图（稀疏）。参赛者需以峰值信噪比（PSNR）为指标优化生成图像与真实图像的保真度。两赛道均采用新发布的Sparse Rendering（SpaRe）数据集及经典的DTU MVS数据集。共有5支团队提交第1赛道结果，4支团队提交第2赛道结果。各参赛模型形式多样，显著推动了当前稀疏神经渲染的技术边界。本文详细介绍了所有参赛模型的设计思路与实验表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。