ICCV 2019 2019

Convolutional Sequence Generation for Skeleton-Based Action Synthesis

ICCV 2019 2019 yysijie/CSGN

It captures the temporal structure at multiple scales through the GP prior and the temporal convolutions; and establishes the spatial connection between the latent vectors and the skeleton graphs via a novel graph refining scheme.

HUMAN ACTION GENERATION

Unsupervised Video Interpolation Using Cycle Consistency

ICCV 2019 2019 NVIDIA/unsupervised-video-interpolation

We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model.

OPTICAL FLOW ESTIMATION VIDEO FRAME INTERPOLATION