SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.01862 · CVPR · 2024

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

Xu He, Zhiyong Wu, Zhiwei Lin, Songcen Xu, Minglei Li, Sicheng Yang, Qiaochu Huang, Xiaofei Wu, Zhensong Zhang, Zhiyi Chen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
thuhcsi/S2G-MDDiffusion — 3 of 3
copy not recorded — 1 of 2
FunctionStatusWhere it lives
identity Ran this paper's copy was not recorded; identical code first harvested from lucidrains/recurrent-memory-transformer-pytorch
pointer only · get_code("7f1040f5e3991d5e")
EMA Ran thuhcsi/S2G-MDDiffusion/inference/model/diffusion.py
code served (permissive licence) · get_code("01c11cf700d39c20")
GestureDiffusion Ran thuhcsi/S2G-MDDiffusion/inference/model/diffusion.py
code served (permissive licence) · get_code("af34e5e7bd22eecd")
make_beta_schedule Ran thuhcsi/S2G-MDDiffusion/inference/model/diffusion.py
code served (permissive licence) · get_code("c984209a2c66afbe")
extract Not yet run this paper's copy was not recorded; identical code first harvested from leekwoon/rgg
pointer only · get_code("09c8479d9a5b3e06")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.01862")
get_code_for_paper("2404.01862")
have("2404.01862")

Connect an agent — have() is free.