代码库
VoMP: Predicting Volumetric Mechanical Property Fields
Python
[CVPR'26] TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
Python
3d-reconstructionnovel-view-synthesis
[NeurIPS 2025] UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
Jupyter Notebook
Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Python
aigcmulti-agentroboticsvideo-gameworldmodel
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Python
diffusion-decoderpixel-diffusion
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Jupyter Notebook
autonomous-drivinggenerationvideo-generation
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
Python
Project Lyra: Open Generative 3D World Models
Python
3ddiffusiongaussiansvideoworld-model
Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework
Jupyter Notebook
genairelightingvideodiffusion
ViPE: Video Pose Engine for Geometric 3D Perception
Python
3dcameradepth-estimationslam
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
Python