Stars
Self-supervised learning for spatial perception
A feed-forward 3D foundation model for reconstructing scenes from streaming data
[ECCV 2026] LoMa: Local Feature Matching Revisited
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Ranking and Covariances for Practical Learned Keypoints
Visual-inertial optimization of VIO trajectories and SLAM maps via accurate sensor modelling, with imu pre-integrated terms, full re-estimation of intrinsics/extrinsics on a generic rig and modelli…
Fast symbolic computation, code generation, and nonlinear optimization for robotics
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Visualize, query, and stream to train on multimodal robotics data.
Reference PyTorch implementation and models for DINOv3
ViPE: Video Pose Engine for Geometric 3D Perception
[ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)
Community list of open-source GNSS software and resources 📡
Release repo for our SLAM Handbook
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
An open source platform for visual-inertial navigation research.
[CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"
GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)
[DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse m…
[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
code for the TOG 2023 paper "Digital 3D Smocking Design"