$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning
Paper
•
2507.13347
•
Published
•
65
Zhou
ZhouTimeMachine
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
VINO: A Unified Visual Generator with Interleaved OmniModal Context
upvoted
a
paper
about 1 month ago
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
upvoted
a
paper
about 2 months ago
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
Organizations
authored
4
papers
4 months ago
DeepVerse: 4D Autoregressive Video Generation as a World Model
Paper
•
2506.01103
•
Published
WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
Paper
•
2509.05296
•
Published
•
7
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Paper
•
2509.12201
•
Published
•
106
authored
a
paper
10 months ago