arxiv:2410.07303
Zhaoyang Huang
DrinkingCoder
AI & ML interests
Optical Flow, Point Tracking, Video Correspondence, Diffusion Models
Recent Activity
upvoted
a
paper
about 1 month ago
GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields
through Efficient Dense 3D Point Tracking
upvoted
a
paper
4 months ago
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
authored
a paper
4 months ago
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
Organizations
None yet
models
1
datasets
None public yet