Stars
Language: Python
Sort by: Most stars
FastAPI framework, high performance, easy to learn, fast to code, ready for production
⚡ A Fast, Extensible Progress Bar for Python and CLI
Graph Neural Network Library for PyTorch
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
Pytorch framework for doing deep learning on point clouds.
An extension of Open3D to address 3D Machine Learning tasks
pySLAM contains a monocular Visual Odometry (VO) pipeline in Python. It supports many modern local features based on Deep Learning.
Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)
Helper functions to create COCO datasets
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scal…
Python implementation of SLAM algorithm Stereo-PTAM
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Python library for computer vision labeling tasks. The core functionality is to translate bounding box annotations between different formats-for example, from coco to yolo.
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection
Automated feature engineering for geospatial data
A tool to transfer Perspective between Equirectangular
Deep learning models for remote sensing applications
SynLiDAR: Synthetic LiDAR sequential point cloud dataset with point-wise annotations (AAAI2022)
BlAInder range scanner is a Blender add-on to simulate Lidar and Sonar measurements. The result can be saved as annotated 2D image or 3D point cloud.
Improved Deep Point Cloud Geometry Compression
The official code repository for paper "Rethinking the Encoding of Satellite Image Time Series".
Convert rgb color mask to polygons per class