Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

🔓 Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation

Inflated i3d network with inception backbone, weights transfered from tensorflow

Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)

Tutorial about 3D convolutional network

lock mechanism with face recognition and liveness detection

A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data

This repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"

This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.

MinkLoc3D: Point Cloud Based Large-Scale Place Recognition

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing (ICCV 2019)

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

MinkLoc3Dv2: Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training

Alzheimer disease diagnosis by Deeply Supervised 3D Convolutional Network

PyTorch Volume Models for 3D data

Pytorch version of the HyperDenseNet deep neural network for multi-modal image segmentation

EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale

A repository with a basic layer of 3D deformable receptive field for 3D VoxCNN and 3D VoxResNet