构建首个支持4K/8K的高质量图文视频数据集，助力超高清视频生成研究。
UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
- 四阶段自动化流程筛选高质量视频并生成9条结构化描述
- 数据集含100+主题、22.4%为8K分辨率，每视频平均824词摘要
- 适配高分辨率视频生成模型训练，推动影视级视频合成发展
视频数据集的质量（图像质量、分辨率、细粒度描述）显著影响视频生成模型的表现。随着视频应用对高质量生成需求提升，如电影级超高清（UHD）视频与4K短视频内容生成，现有公开数据集已无法满足研究与应用需求。本文首次提出一个开源的高质量文本到视频数据集UltraVideo，支持UHD-4K（其中22.4%为8K），涵盖100多种主题，每个视频配备9条结构化描述及1条总结性描述（平均824词）。我们设计了四阶段高度自动化的数据清洗流程：（i）多样化高质量视频片段收集；（ii）基于统计特征过滤；（iii）模型驱动的数据净化；（iv）生成全面且结构化的标题。此外，我们扩展了Wan模型为UltraWan-1K/-4K，可原生生成高质量1K/4K视频，且文本控制更一致，验证了数据清洗的有效性。UltraVideo数据集与UltraWan模型已开放获取。
原文摘要 · Abstract (English)
The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. However, the existing public datasets cannot support related research and applications. In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\% of which are 8K) text-to-video dataset named UltraVideo, which contains a wide range of topics (more than 100 kinds), and each video has 9 structured captions with one summarized caption (average of 824 words). Specifically, we carefully design a highly automated curation process with four stages to obtain the final high-quality dataset: \textit{i)} collection of diverse and high-quality video clips. \textit{ii)} statistical data filtering. \textit{iii)} model-based data purification. \textit{iv)} generation of comprehensive, structured captions. In addition, we expand Wan to UltraWan-1K/-4K, which can natively generate high-quality 1K/4K videos with more consistent text controllability, demonstrating the effectiveness of our data curation.We believe that this work can make a significant contribution to future research on UHD video generation. UltraVideo dataset and UltraWan models are available at https://xzc-zju.github.io/projects/UltraVideo.
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。