The P3 Dataset: Pixels, Points and Polygons for Multimodal Building Vectorization

Effortless data labeling with AI support from Segment Anything and other awesome models.

my little YOLO annotator with some nice automation

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Python library for cleaning and regularising building footprints in geospatial data, aligning edges to principal directions and simplifying polygons for more accurate analysis.

Opensource WebGIS Development Learning Roadmap

Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding

[CVPR 2025] Towards Satellite Image Road Graph Extraction: A Global-Scale Dataset and A Novel Method

Official repo of paper RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement

Segment Anything Model for large-scale, vectorized road network extraction from aerial imagery. CVPRW 2024

Official implementation of "Global Collinearity-aware Polygonizer for Polygonal Building Mapping in Remote Sensing"

Mixture Density Network for water constituent estimation

A library to access OpenStreetMap related services

WalnutData: Published by the Laboratory of Computer Vision and Intelligent Perception, School of Information, Yunnan Normal University.

This reposiotry is the collection for public 3D LiDAR datasets

Earth Observation Training Datasets

Fast Segment Anything

GeoAI: Artificial Intelligence for Geospatial Data

Benchmarking of weather forecasts based on station observations

CVPR 2023 Data Contribution

[CVPR 2024 🔥] GeoChat, the first grounded Large Vision Language Model for Remote Sensing

Orthogonalize polygon in python by making all its angles 90 or 180 deg

Kepler.gl is a powerful open source geospatial analysis tool for large-scale data sets.

A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

An extension of Open3D to address 3D Machine Learning tasks

A toolkit that enables building damage assessments from remotely sensed imagery.

[ESSD 2025 & IEEE GRSS DFC 2025] Bright: A globally distributed multimodal VHR dataset for all-weather disaster response