search

yzhq97 / transmomo.pytorch

This is the official PyTorch implementation of the CVPR 2020 paper "TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting".
https://yzhq97.github.io/transmomo/
392 stars 54 forks source link

Questions about latent space interpolation results #12

Closed kangyeolk closed 3 years ago

kangyeolk commented 3 years ago

Hi, first of all, thank you for releasing such a great code! My question regarding the latent space interpolation is that how the background of the interpolated pose changes. For example Figure 8 in the paper, I can see body structures can be successfully interpolated, but what about the synthesized frames conditioned on them? It would be helpful if you can provide or describe the synthesized video frame. (Is it just a mixture of two frames??)

Walter0807 commented 3 years ago

Hi, thank you for your interest in our work. Note that interpolation is applied on skeleton level, and the decoded skeletons share the skeleton-to-video renderers, so the textures would not be influenced by pose interpolation. However, if the structure is interpolated, the size mismatch would likely cause artifacts on generated frames.