A toolkit for preprocessing, training and inference
-
Updated
May 22, 2024 - Python
A toolkit for preprocessing, training and inference
Project examing sparse deep learning architectures for ligand classification.
3D Reconstruction and Classification from Very High Resolution Satellite Imagery (ReKlaSat 3D)
Generalizable Stable Points Segmentation for 3D LiDAR Scan-to-Map Long-Term Localization
MINSU3D: MinkowskiEngine-powered Scene Understanding in 3D
EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale
MinkLoc3Dv2: Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation (RAL 2023)
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
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."