[ICLR 2026] Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

[CVPR26] 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 Cambr…

[IEEE TIP 2021] Iterative Robust Graph for Unsupervised Change Detection of Heterogeneous Remote Sensing Images

[ISPRS P&RS 2025] Rules-Induced Energy Model (RIEM) for Multimodal Change Detection

OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery

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

High Speed Assessment and Satellite Tracking for Emergencies

Citation Extraction & Reference Checking Assistant

[CVPR 2026 Oral] "INSID3: Training-Free In-Context Segmentation with DINOv3"

Run neural networks via GDAL CLI

Official Implementation of Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

Code for GEO-Bench V2 datasets. Made in collaboration with TUM, IBM and ServiceNow.

Implementation of a binary change detection system for EO-SAR image pairs using U-Net with ResNet34 backbone, PyTorch, and multimodal satellite imagery segmentation.

Remote Sensing Change Net is a PyTorch-based change detection project for remote sensing imagery, using a Siamese transformer architecture to detect pixel-level changes between bi-temporal satellit…

Code Repo for Earth Observation for Disaster Mapping: Benchmarks, Methods, Challenges and Future Perspectives

[IEEE TGRS 2024] Learning Land-Cover Changes from Satellite and Map Data via Object-Guided Transformer

[CVPR 2026] UniChange: Unifying Change Detection with Multimodal Large Language Model

[CVPR 2025] Official Implementation of "Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection". The first multi-class UAD model that can compete with single-class SOTAs

Official repo for the paper "No One Knows the State-of-the-Art in Geospatial Foundation Models"

[CVPR 2026 Oral] VGGT Omega

Dinomaly2: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection

Faiss Multilabel and Multiclass KNN Classifier Implementations

Code repository for paper "Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance". Code, data and model weights will be made public soon.

SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation

OmniOVCD