A generative world for general-purpose robotics & embodied AI learning.

[ARXIV'24] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

[ARXIV'24] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

official implementation of paper "Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation"

DressRecon: Freeform 4D Human Reconstruction from Monocular Video

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

CUDA accelerated rasterization of gaussian splatting

[NeurIPS 2024] Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels

Code for PhysDreamer

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Awesome papers for markerless animal motion capture and 3D reconstruction.

Pyramidal Neural Radiance Fields

Web-based 3D visualization + Python

[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

🎠 MagicPony: Learning Articulated 3D Animals in the Wild (CVPR 2023)

Distilling Neural Fields for Real-Time Articulated Shape Reconstruction (CVPR 2023)

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

Scalable Urban Dynamic Scenes

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

Code Release for RelPose++: Recovering 6D Poses from Sparse-view Observations

a pytorch cuda extension for fast (dual) quaternion operations

[ICCV 2023] Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)