Few-shot Video-to-Video Synthesis

NeurIPS 2019 Ting-Chun WangMing-Yu LiuAndrew TaoGuilin LiuJan KautzBryan Catanzaro

Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Video-to-Video Synthesis Street Scene Few-shot Video-to-Video FID 144.24 # 1
Video-to-Video Synthesis YouTube Dancing Few-shot Video-to-Video FID 80.44 # 1