Datasets > Modality > Videos > FVI (Free-form Video Inpainting)

FVI (Free-form Video Inpainting)

Introduced by Chang et al. in Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN

The Free-Form Video Inpainting dataset is a dataset used for training and evaluation video inpainting models. It consists of 1940 videos from the YouTube-VOS dataset and 12,600 videos from the YouTube-BoundingBoxes.

Source: https://arxiv.org/abs/1904.10247

Samples

License

  • Unknown

Modalities

Languages

Tasks

Similar Datasets