Stars
Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRouter — one command, any provider. Works with coding agents, OpenClaw, Hermes, and others.
OCR, layout analysis, reading order, table recognition in 90+ languages
Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization (Line Transformer)
Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).
Open Source Graph Neural Net Based Pipeline for Image Matching
[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
AWS virtual infrastructure simulator for training reinforcement learning based cloud capacity management systems
Fast and accurate python RANSAC with LO, LAF-check
Hummingbird compiles trained ML models into tensor computation for faster inference.
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
PhotoSynth Dataset for improving local patch Descriptors
Official implementation of "Content-Consistent Generation of Realistic Eyes with Style", ICCW 2019
Public implementation of "Beyond Cartesian Representations for Local Descriptors", ICCV 2019
Comparison of the matching strategies for local feature descriptor
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…
Simple function for local patch extraction from OpenCV keypoints.
Differentiable bitonic sorting
The best design tools and plugins for everything 👉
Helper scripts for participation in http://cvg.dsi.unifi.it/cvg/index.php?id=caip-2019-contest
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
Humpback Whale Identification
MODS with external deep descriptors/detectors
Code for CVPR 2018 paper "Hashing as Tie-Aware Learning to Rank"