MineRL

Description

Example completions, starting from the first 36 frames of a test video. Within each block each column shows completions for a different test video. The top row is the ground-truth and all other rows are sampled completions. Observed frames are marked with a red border.

Discussion

Samples from CWVAE quickly become blurry, unlike FDM or VDM samples. There are otherwise no obvious qualitative differences between the methods on this dataset.

FDM with Autoreg

FDM with Hierarchy-2

CWVAE

VDM