Stars
ViPE: Video Pose Engine for Geometric 3D Perception
Code of π^3: Permutation-Equivariant Visual Geometry Learning
Towards a Generative 3D World Engine for Embodied Intelligence
Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
A web viewer to explore latent spaces of generative 3DGS models
[arXiv 2024] Novel View Extrapolation with Video Diffusion Priors
Sample viewer implementing several rendering methods for 3D gaussians using Vulkan API
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Code release for paper "Test-Time Training Done Right"
LichtFeld Studio: Where reality and the digital world blend.
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Lets make video diffusion practical!
Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
[SIGGRAPH'25] Official implementation for the paper "Deformable Beta Splatting"
A Modular Toolkit for Robot Kinematic Optimization
A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer
[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
A refactored codebase for Gaussian Splatting. Fastest, Better, Modular, Pure Python or CUDA Extension
Ray tracing and hybrid rasterization of Gaussian particles
Stable Virtual Camera: Generative View Synthesis with Diffusion Models
A high-throughput and memory-efficient inference and serving engine for LLMs