Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis, including human motion imitation, appearance transfer, and novel view synthesis. Currently the paper is under review of IEEE TPAMI. It is an extension of our previous ICCV project impersonator, and it has a more powerful ability in generalization and produces higher-resolution results (512 x 512, 1024 x 1024) than the previous ICCV version.
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis, including human motion imitation…
Google Colab (Famous propeller dance in Japan)
source movie: mp4
source image: one image/two images(This GoogleColab is using two images)
The following is the result I tried.
If you have GPU, you can run iPERCore on your local machine.