Co-speech Gesture Video Generation with 3D Human Meshes

1 Carnegie Mellon University    2 University of Science and Technology of China   
3 Ping An Technology    4 PAII Inc.

ECCV 2024

Back

Our Results (Mesh to Video)

We show results of generated texture map and generated video by our mehotd from a given untextured mesh sequence. We also provide the corresponding ground-truth video for comparison.

Input Mesh

Textured Mesh

Generated Video

Ground Truth Video

Oliver


Input Mesh

Textured Mesh

Generated Video

Ground Truth Video

Conan


Input Mesh

Textured Mesh

Generated Video

Ground Truth Video

Seth


Input Mesh

Textured Mesh

Generated Video

Ground Truth Video

Chemistry