360VFI
收藏资源简介:
360VFI数据集由武汉大学等机构创建,专门用于全方位视频帧插值研究。该数据集包含930个三元组样本,涵盖多种运动和内容,主要用于解决低帧率全方位视频导致的用户体验问题。数据集通过整合多个来源的视频数据,经过精心筛选和处理,以适应全方位视频插值的需求。其创建过程考虑了全方位视频特有的扭曲特性,旨在通过模型训练提高视频插值的效率和质量。
The 360VFI dataset was developed by institutions including Wuhan University, and is specifically designed for omnidirectional video frame interpolation research. This dataset contains 930 triplet samples covering diverse motions and content, mainly aimed at resolving user experience issues caused by low-frame-rate omnidirectional videos. It integrates video data from multiple sources, and has undergone rigorous screening and processing to meet the requirements of omnidirectional video frame interpolation. Its development process takes into account the unique distortion characteristics of omnidirectional videos, with the aim of improving the efficiency and quality of video frame interpolation through model training.

- 1360VFI: A Dataset and Benchmark for Omnidirectional Video Frame Interpolation武汉大学 · 2024年



