GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

A library for efficient similarity search and clustering of dense vectors.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[CVPR 2025] CRISP: Object Pose and Shape Estimation with Test-Time Adaptation

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Builder and index for PyTorch packages

[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Personalized Representation from Personalized Generation (ICLR 2025)

Uses Unreal Engine & Cesium to generate large synthetic dataset from 3D meshes. Enables machine learning tasks like Visual Place Recognition read more in our paper on this: https://meshvpr.github.io

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation

CUDA accelerated rasterization of gaussian splatting

Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

[3DV 2025, Oral] LoopSplat: Loop Closure by Registering 3D Gaussian Splats

An open source implementation of CLIP.

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

Feature splatting based on INRIA GS rasterizer

A static website generator for people who enjoy the simpler things in life.

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds