Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
-
Updated
Mar 5, 2024 - Python
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation (RAL 2023)
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
MinkLoc3Dv2: Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale
MINSU3D: MinkowskiEngine-powered Scene Understanding in 3D
Generalizable Stable Points Segmentation for 3D LiDAR Scan-to-Map Long-Term Localization
3D Reconstruction and Classification from Very High Resolution Satellite Imagery (ReKlaSat 3D)
Project examing sparse deep learning architectures for ligand classification.
A toolkit for preprocessing, training and inference
Add a description, image, and links to the minkowski-engine topic page so that developers can more easily learn about it.
To associate your repository with the minkowski-engine topic, visit your repo's landing page and select "manage topics."