SALAD: Skeleton-aware Latent Diffusion
What it is
SALAD is a motion generation and editing framework that uses a skeleton-aware latent diffusion model. It generates and edits human motion based on text descriptions by leveraging a latent space that captures skeletal dynamics.
The problem it solves
Difficulties in generating and editing high-quality, diverse human motions from text while maintaining skeletal consistency.
What you could use it for
- Text-to-motion generation for 3D human animations
- Editing existing motion sequences based on text prompts
- Generating high-quality human motion for games and animations
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.