Stars
Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.
Pilot course for Robotics 101: Computational Linear Algebra
Copper is a user friendly and deterministic runtime for building production-ready robots.
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
SE3ET: SE(3)-Equivariant Transformer for Low-Overlap Point Cloud Registration
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
[NeurIPS 2024] A Generalizable World Model for Autonomous Driving
Parallel algorithm for solving LQR problems using recursive Schur Compliments
A versatile and efficient C++ library for real-time constrained trajectory optimization
Simple jupyter notebook for 3D reconstruction using kornia and pycolmap
Multi-camera calibration using one or more calibration patterns
Gauzilla: a 3D Gaussian Splatting renderer written in Rust for WebAssembly with lock-free multithreading
Optimal Transport Aggregation for Visual Place Recognition
Dense matching library based on PyTorch
Vehicle State Estimation using Error-State Extended Kalman Filter
Dead Reckoning In Field Time: Symmetry-Preserving State Estimation Library for Various Robotic Platforms
Training library for local feature detection and matching
This is the repo for the following paper: Ming-Fang Chang, Akash Sharma, Michael Kaess, and Simon Lucey. Neural Radiance Fields with LiDAR Maps. ICCV 2023
Trying out the Mamba architecture on small examples (cifar-10, shakespeare char level etc.)
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
[CVPR 2024] A world model for autonomous driving.
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
A minimal implementation of diffusion models for text generation
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.