构建首个生成模型驱动的短视频修复基准，推动真实场景下视频质量提升。
NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results
- 提出KwaiVIR数据集，包含合成与真实短视频样本。
- 200条合成训练视频、48条真实训练视频，测试集含20条视频。
- 支持主观与客观双评估，吸引95支队伍参赛，12队提交有效方案。
本文概述了NTIRE 2026年关于生成模型驱动的短形式用户生成视频（S-UGC）野外修复挑战赛。该挑战赛采用由中科大与快手科技共同贡献的新基准数据集KwaiVIR，包含合成失真视频和真实世界中的短形式UGC视频。本次发布数据包括200条合成训练视频、48条野外训练视频、11条验证视频和20条测试视频。挑战目标是建立一个强大且实用的基准，用于在复杂真实退化条件下恢复短形式UGC视频，特别是在生成模型新兴范式下的应用。比赛设两个赛道：主赛道为基于用户研究的主观评价，次赛道为客观评估。共有95支团队注册，12支队伍提交了有效的最终解决方案与技术报告。所提交方法在KwaiVIR基准上表现优异，展示了短形式UGC视频野外修复的显著进展。
原文摘要 · Abstract (English)
This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.
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。