Stars
This open-source package provides a framework for automatically detecting and extracting metadata from solar array installations in satellite images.
Code associated with the paper titled "A high-performance neuroprosthesis for speech decoding and avatar control" , published in Nature in 2023.
Roof Information Dataset for CV-Based Photovoltaic Potential Assessment
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
The methodology behind a supervised deep learning model that generates 3D pointclouds out of 2D aerial images of buildings.
Make your models invariant to changes in scale.
Laspy is a pythonic interface for reading/modifying/creating .LAS LIDAR files matching specification 1.0-1.4.
PyTorch 1.0 implementation of the approximate Earth Mover's Distance
Worldwide building footprints derived from satellite imagery
Building footprint segmentation from satellite and aerial imagery
A sample project demonstrating how to extract building footprints from satellite images using a semantic segmentation model. Data from the SpaceNet Challenge.
PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
Official implementation of GraphX-Convolution
Pytorch code to construct a 3D point cloud model from single RGB image.
PyTorch models and pipeline developed for "DeepSolar for Germany". For reference, the paper can found at https://ieeexplore.ieee.org/document/9203258
2019 IEEE GRSS Data Fusion Contest data, baselines, and metrics
Training dataset for supervised learning
CosmiQ Works Geospatial Machine Learning Analysis Toolkit
Open citygml data for the United States
Robust Speech Recognition via Large-Scale Weak Supervision
📃Language Model based sentences scoring library