The code for the paper "Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models" (ICCV'23).

NNDL Project - 3D Object Classification

RandAugment process for point cloud data to handle with 3D classification task

MeshRunner - Improved classification of 3D mesh objects

Solution of team tara: Public 7th, Private 13th (The renewed pipeline scores 8th place)

This repository is for the Deep learning(Classification & XAI) part with 3D OCTA volumes.

Implementation of Multi-view CNN for 3D classification evaluated on MoodleNet40 dataset.

ModelNet10 classification method based on rendered videos.

A rule-based algorithm enabled the automatic extraction of disease labels from tens of thousands of radiology reports. These weak labels were used to create deep learning models to classify multiple diseases for three different organ systems in body CT.

This package implements deep learning modules for medical imaging application in PyTorch (miTorch).

A fast and low memory requirement version of PointHop and PointHop++, which is built upon Apache Spark.

3D MNIST Point Cloud Classifier using 3D ConvNet with Swift for TensorFlow

Automated detection of focal cortical dysplasia

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

3D Face Classification with Graph Neural Networks

Weakly supervised 3D classification of multi-disease chest CT scans using multi-resolution deep segmentation features via dual-stage CNN architecture (DenseVNet, 3D Residual U-Net).

PyTorch Volume Models for 3D data

PointHop: An Explainable Machine Learning Method for Point Cloud Classification

This is the official repository of the original Point Transformer architecture.

A new approach for retrieval and classification of 3D models that directly performs in the CAD format without any format conversion to other representations like point clouds of meshes, thus avoiding any loss of information.