PyTorch code and models for VJEPA2 self-supervised learning from video.

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Code release for NeuS

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

ViPE: Video Pose Engine for Geometric 3D Perception

[TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

Code of π^3: Permutation-Equivariant Visual Geometry Learning

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/ab…

Official implementation of Continuous 3D Perception Model with Persistent State

Mobile manipulation research tools for roboticists

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

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

[3DV'25] 3D Reconstruction with Spatial Memory

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

Training library for local feature detection and matching

[3DV 2025] Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent Sitzmann

[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]

The devkit of the nuPlan dataset.