Zhiyong Wang, Kun Hu, Chengjiang Long, Clinton Mo
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision. The action features are often derivable accurately from the full series of keyframes, and thus, leveraging the global context with transformers has been a promising data-driven embedding approach. However, existing methods are often with inputs of interpolated intermediate frame for continuity using basic interpolation methods with keyframes, which result in a trivial local minimum during training. In this paper, we propose a novel framework to formulate latent motion manifolds with keyframe-based constraints, from which the continuous nature of intermediate token representations is considered. Particularly, our proposed framework consists of two stages for identifying a latent motion subspace, i.e., a keyframe encoding stage and an intermediate token generation stage, and a subsequent motion synthesis stage to extrapolate and compose motion data from manifolds. Through our extensive experiments conducted on both the LaFAN1 and CMU Mocap datasets, our proposed method demonstrates both superior interpolation accuracy and high visual similarity to ground truth motions.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.14926")
get_code_for_paper("2303.14926")
have("2303.14926")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.14926.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.14926)
Connect an agent — have() is free.