04:00
2026-07-31
arxiv.org
generative-ai
4DHumanDiff: Direct Text-to-4DGS Generation for Consistent 360-Degree Dynamic Humans
Researchers introduced 4DHumanDiff, a diffusion framework that directly generates dynamic human assets represented by 4D Gaussian Splatting (4DGS) from text prompts, avoiding video pre-generation and …