Python Earth Observation processing chain

A dependency-free large (+2500) collection of colormaps and palettes for Python 🎨

Diffusion-based Tree Skeletonization

code to load the SSL4EO-EU-Forest dataset from HuggingFace, cf. https://huggingface.co/datasets/dm4eo/ssl4eo_eu_forest

Bayesian Ecological Modeling in Python

DiffusionFastForward: a free course and experimental framework for diffusion-based generative models

A high-performance implementation of 3D RANSAC (Random Sample Consensus) algorithm using PyTorch and CUDA.

fluids v.3

A GPU-native algorithm for accelerated low-dimensional kNN

TESSERA is a foundation model that can process time-series satellite imagery for applications such as land classification and canopy height prediction. Developed at the University of Cambridge, it …

H-Net: Hierarchical Network with Dynamic Chunking

Chat2Geo delivers a ChatGPT-like experience tailored for remote-sensing-based geospatial analysis. Its mission is to democratize geospatial insights at scale by harnessing cutting-edge AI technolog…

Welcome to NeuCo-Bench, a benchmarking framework for evaluating compressed embeddings on downstream tasks.

Manage, search, and download Earth Observation data with Φ-down from Copernicus missions with ease and efficiency.

NestEO: Nested and Aligned Earth Observation Framework with Multimodal Dataset

Sentinel-1 & Sentinel-2 data cubes at large scale (bigger-than-memory) on any machine with integrated cloud detection, snow masking, harmonization, merging, and temporal composites.

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

[🌳Software] A novice-friendly interative tree modeling system based on modular procedural graphs.

Codebase of our paper in CVPR 2025: "Neural Hierarchial Decomposition for Single Image Plant Modeling."

(EarthVision 2025 - CVPR Workshop) Official repository of DAFA-LS, a dataset of satellite image time series for the task of archaeological looting detection.

The official repository for tariff

Towards Robust Evaluation for Geospatial Foundation Models

GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidance

[ISPRS 2024] Sat-SINR: High-Resolution Species Distribution Models through Satellite Imagery

GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidance

Code to "Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks" at the ICLR 2025 Workshop: Tackling Climate Change with Machine Learning.

Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"