9_No_subdomain

Fig.9. Ablation study: when no sub-domain label is used during training and testing.

The first video is the input semantic label sequence, the rest videos are the translated scene videos with style codes randomly sampled from the prior distribution. There are 220 frames for each video.

UVIT
UVIT
Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning