GANs for Temporal Self-Supervision of Videos

This is a talk by Nils Thuerey for the CLIC CVPR 2020 workshop: Motivated by time-dependent problems from the physics area, we especially focuse on spatio-temporal data such as videos. Here, self-supervision in space, as well as time, has shown lots of promise, e.g., in the form of the TecoGAN model, which can handle video super-resolution and unpaired video translation, among others. This is the video of a talk given at the CLIP workshop at CVPR 2020, where we demonstrate generative adversarial networks for video super-resolution, as well as unpaired video translation. In addition, we've targeted improved evaluation metrics for video content. In particular, Nils highlights our choice of a perceptual metric (such as LPIPS), in addition to a temporal perceptual evaluation (tLP) and a motion estimate (tOF). We've tested these across a range of examples and verified their rankings with user studies. Details at: https://ge.in.tum.de/publications/201... , and source code at https://github.com/thunil/TecoGAN.