Papers › From Here to There: Video Inbetweening Using Direct 3D Convolutions

From Here to There: Video Inbetweening Using Direct 3D Convolutions

24 May 2019arXiv:1905.10240archive 2025-07-28

Yunpeng Li, Dominik Roblek, Marco Tagliasacchi

We consider the problem of generating plausible and diverse video sequences, when we are only given a start and an end frame. This task is also known as inbetweening, and it belongs to the broader area of stochastic video generation, which is generally approached by means of recurrent neural networks (RNN). In this paper, we propose instead a fully convolutional model to generate video sequences directly in the pixel domain. We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames. Our model learns to produce such latent representation by progressively increasing the temporal resolution, and then decode in the spatiotemporal domain using 3D convolutions. The model is trained end-to-end by minimizing an adversarial loss. Experiments on several widely-used benchmark datasets show that it is able to generate meaningful and diverse in-between video sequences, according to both quantitative and qualitative evaluations.

PaperPDFCode

Code

xih108/Video_Completion mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Video Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

3D Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections