Starred repositories
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Configs and boilerplates for Label Studio's Machine Learning backend
LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation
Accurate, detailed, and automatic modelling of laser-scanned trees
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Various pieces of code for making life simpler with the Eagle lidar scanner
SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
Good Keypoints for the Two-View Geometry Estimation Problem. The reference implementation of the preprint.
Code repository for "DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers"
Training library for local feature detection and matching
Code release for CVPR'24 submission 'OmniGlue'
[CVPR 2025] JamMa is a lightweight image matcher that enables fast internal and mutual interaction of images with joint Mamba.
[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
The state-of-the-art image restoration model without nonlinear activation functions.
a simple tool (LGPL) to validate whether LAS/LAZ files conform to the LAS specification
Implementation of "Learning to Make Keypoints Sub-Pixel Accurate" (ECCV 2024).
[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image
A steerer for D-dimensional keypoint descriptions is a DxD matrix that transforms the descriptions as if they were computed from a rotated image.
[ICCV 2025] MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
Bibliographic list for papers of image matching
Public release of the Image Matching Benchmark: https://image-matching-challenge.github.io
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation