Stars
Implement of the paper "Integrating SAM with Feature Interaction for Remote Sensing Change Detection"
Referring Change Detection in Remote Sensing Imagery
Fast, Modern, and Low Precision PyTorch Optimizers
A CNN-transformer Network with Multi-scale Context Aggregation for Fine-grained Cropland Change Detection
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
[AAAI 2026 Oral] DynamicEarth: How Far are We from Open-Vocabulary Change Detection?
SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
COLMAP - Structure-from-Motion and Multi-View Stereo
Training code for "Radiance Meshes for Volumetric Reconstruction".
[arXiv'25] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
Official code repository of Sen12Landslides
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation(ICML 2025)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
The official pytorch implementation of the paper "ChangeDINO: DINOv3-Driven Building Change Detection in Optical Remote Sensing Imagery."
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
This repo holds the whole code to reproduce the research performed in the FFG-project "Habitalp 2.0"
Release for Improved Denoising Diffusion Probabilistic Models
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Self-contained, minimalistic implementation of diffusion models with Pytorch.
Minimal implementation of scalable rectified flow transformers, based on SD3's approach
Earth system foundation model data, training, and eval
😎 Awesome lists about all kinds of interesting topics
A comprehensive and up-to-date compilation of datasets, tools, methods, review papers, and competitions for remote sensing change detection.