Vimeo-90k Dataset 一个大规模、高质量的视频数据集

一个大规模、高质量的视频数据集Vimeo90K。这个数据集由从vimeo.com下载的8.98万个视频片段组成，其中包含大量场景和动作。它设计用于以下四个视频处理任务：时间帧插值、视频去噪、视频去块和视频超分辨率。 Vimeo90K数据集结构： 1、Triplet dataset (for temporal frame interpolation): The triplet dataset consists of 73,171 3-frame sequences with a fixed resolution of 448 x 256, extracted from 15K selected video clips from Vimeo-90K. This dataset is designed for temporal frame interpolation. Download links are 2、Septuplet dataset (for video denoising, deblocking, and super-resoluttion): Notice: we have recently updated our testing denoising dataset to fix a bug in denoising test data generation. The new quantitative result of our algorithm is reported in our updated paper The septuplet dataset consists of 91,701 7-frame sequences with fixed resolution 448 x 256, extracted from 39K selected video clips from Vimeo-90K. This dataset is designed to video denoising, deblocking, and super-resolution. Abstract Many video processing algorithms rely on optical flow to register different frames within a sequence. However, a precise estimation of optical flow is often neither tractable nor optimal for a particular task. In this paper, we propose task-oriented flow (TOFlow), a flow representation tailored for specific video processing tasks. We design a neural network with a motion estimation component and a video processing component. These two parts can be jointly trained in a self-supervised manner to facilitate learning of the proposed TOFlow. We demonstrate that TOFlow outperforms the traditional optical flow on three different video processing tasks: frame interpolation, video denoising/deblocking, and video super-resolution. We also introduce Vimeo-90K, a large-scale, high-quality video dataset for video processing to better evaluate the proposed algorithm. @article{xue2019video, title={Video Enhancement with Task-Oriented Flow}, author={Xue, Tianfan and Chen, Baian and Wu, Jiajun and Wei, Donglai and Freeman, William T}, journal={International Journal of Computer Vision (IJCV)}, volume={127}, number={8}, pages={1106--1125}, year={2019}, publisher={Springer} }

大规模高质量视频数据集Vimeo90K（Vimeo90K）包含从vimeo.com下载的8.98万个视频片段，涵盖丰富多样的场景与动作类型。该数据集被设计用于四类视频处理任务：时间帧插值、视频去噪、视频去块以及视频超分辨率。

Vimeo90K数据集结构如下：
1、 三元组数据集（Triplet dataset）（用于时间帧插值）：该三元组数据集包含73171个固定分辨率为448×256的3帧序列，从Vimeo90K中精选的1.5万个视频片段中提取而来，专为时间帧插值任务设计。下载链接为
2、 七元组数据集（Septuplet dataset）（用于视频去噪、去块与超分辨率）：注意：我们近期更新了去噪测试数据集，以修复去噪测试数据生成过程中的一处缺陷。我们算法的最新量化结果已在更新后的论文中公布。该七元组数据集包含91701个固定分辨率为448×256的7帧序列，从Vimeo90K中精选的3.9万个视频片段中提取而来，专为视频去噪、去块及超分辨率任务设计。

摘要
诸多视频处理算法依赖光流（optical flow）来配准视频序列中的不同帧。然而，针对特定任务而言，精确估计光流往往既难以实现，也并非最优方案。本文提出了面向任务的光流（Task-Oriented Flow，TOFlow），一种为特定视频处理任务量身定制的光流表示方法。我们设计了一款包含运动估计模块与视频处理模块的神经网络，这两个模块可通过自监督方式联合训练，以助力所提TOFlow的学习。实验表明，在三类不同的视频处理任务（帧插值、视频去噪/去块以及视频超分辨率）中，TOFlow的性能均优于传统光流方法。本文同时介绍了Vimeo90K——一款用于视频处理的大规模高质量视频数据集，以更好地评估所提算法。

@article{xue2019video, 标题={面向任务的光流视频增强}, 作者={Xue, Tianfan、Chen, Baian、Wu, Jiajun、Wei, Donglai、Freeman, William T}, 期刊={国际计算机视觉杂志（International Journal of Computer Vision, IJCV）}, 卷={127}, 期={8}, 页码={1106--1125}, 年份={2019}, 出版商={Springer} }

搜集汇总

背景与挑战

背景概述

Vimeo-90k是一个包含8.98万个视频片段的大规模、高质量数据集，主要用于时间帧插值、视频去噪、视频去块和视频超分辨率等视频处理任务。数据集分为Triplet和Septuplet两部分，分别针对不同的视频处理需求。