arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.09754cs.CV
收藏

LAVIB:一个大规模视频插值基准

LAVIB: A Large-scale Video Interpolation Benchmark

University of Twente(特温特大学)

Alexandros Stergiou

AI总结:

本文提出大规模视频插值基准 LAVIB,包含 283K 个超高清视频片段,并基于运动、光照、清晰度和对比度指标构建分布外挑战,以推动视频帧插值研究。

摘要:

本文为视频帧插值(VFI)这一低级视频任务引入了一个大规模视频插值基准(LAVIB)。LAVIB 包含通过网络自动流水线采集的大量高分辨率视频,且对人工验证的要求极低。针对每个视频的运动幅度、光照条件、帧清晰度和对比度均计算了相应指标。当前的低级视频任务数据集对视频的收集以及基于这些指标构建定量挑战的探索尚不充分。LAVIB 总共包含来自 17K 个超高清视频的 283K 个片段,时长覆盖 77.6 小时。基准的训练集、验证集和测试集保持相似的视频指标分布。此外,还针对分布外(OOD)挑战创建了进一步划分,其训练集和测试集包含属性不相似的视频。

英文摘要:

This paper introduces a LArge-scale Video Interpolation Benchmark (LAVIB) for the low-level video task of Video Frame Interpolation (VFI). LAVIB comprises a large collection of high-resolution videos sourced from the web through an automated pipeline with minimal requirements for human verification. Metrics are computed for each video's motion magnitudes, luminance conditions, frame sharpness, and contrast. The collection of videos and the creation of quantitative challenges based on these metrics are under-explored by current low-level video task datasets. In total, LAVIB includes 283K clips from 17K ultra-HD videos, covering 77.6 hours. Benchmark train, val, and test sets maintain similar video metric distributions. Further splits are also created for out-of-distribution (OOD) challenges, with train and test splits including videos of dissimilar attributes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑