Ultralytics YOLO 🚀

OpenMMLab Detection Toolbox and Benchmark

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

Fast Segment Anything

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

User-friendly, commercial-grade software for processing aerial imagery. ✈️

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!

OpenMMLab Model Deployment Framework

OpenMMLab Rotated Object Detection Toolbox and Benchmark

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer TPAMI - HAT: Hybrid Attention Transformer for Image Restoration

D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction

Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc., supportin…

Richer Convolutional Features for Edge Detection model in pytorch CVPR2017

xLSTM as Generic Vision Backbone

Falcon: A Remote Sensing Vision-Language Foundation Model

The official repo for [TPAMI'25] "HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model"

Official code of Remote Sensing Mamba

The pytorch implementation for "SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images"

Python scripts for the Segment Anythin 2 (SAM2) model in ONNX

A bitmap vectorizer that can trace along the centerline of a stroke. The builtin inkscape 'trace bitmap' can only trace edges, thus resulting in double lines for most basic use cases. It uses 'auto…

detectron2 windows build

[IEEE TGRS 2024] EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution

Deepness is a remote sensing plugin that enables deep learning inference in QGIS

Building Segmentation Post-processing -- Contour regularization.

This is an official implementation for "HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery" (CVPR2025)

QGIS plugin for the SamGeo Python package

[CVPR 2025] Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images