Import a 3D Model and automatically assign and export animations

Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation (ICCV 2025)

Official code for paper "InstantSfM: Fully Sparse and Parallel Structure-from-Motion"

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction

An unified model for 4D human-scene reconstruction

Workflow to convert an OSM file from OpenStreetMap into a .pcd file, lanelet2 file and a 3D Model suitable for Autoware and AWSIM.

A simple state update rule to enhance length generalization for CUT3R

MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025)

Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

[RA-L 2023] EasyHeC: Accurate and Automatic Hand-eye Calibration via Differentiable Rendering and Space Exploration

Fast, automatic, accurate camera calibration. A simplified and expanded version of EasyHec

Code of WinT3R: Window-Based Streaming Rrconstruction With Camera Token Pool

[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking

JavaScript animation engine

Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

🤳 VR/AR for react-three-fiber

ViPE: Video Pose Engine for Geometric 3D Perception

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

[ICCV 2025 Highlight] No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

Official code of "ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction", IJCAI2025

Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"

(ICCV 25) MonoFusion

Cameras as Relative Positional Encoding

[CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.