Select Language

公开数据集

Vimeo-90k Dataset  一个大规模、高质量的视频数据集

Vimeo-90k Dataset 一个大规模、高质量的视频数据集

Scene:

Music Analysis,Action/Event Detection,Depth Estimation

Data Type:

Classification
所需积分:100 去赚积分?
  • 138浏览
  • 0下载
  • 0点赞
  • 收藏
  • 分享

贡献者查看主页

Massachusetts Institute of Technology

The MIT community is driven by a shared purpose: to make a better world through education, research, and innovation. We are fun and quirky, elite but not elitist, inventive and artistic, obsessed with numbers, and welcoming to talented people regardless o

Data Preview ? 159G

    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

    • Testing set only (17GB): zip

    • Both training and test set (33GB): zip

    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.

    • The test set for video denoising (16GB): zip

    • The test set for video deblocking (11GB): zip

    • The test set for video super-resolution (6GB): zip

    • The original test set (not downsampled or downgraded by noise) (15GB): zip

    • The original training + test set (82GB): zip

    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}
    }





    0相关评论