Name: Matt De Vries
Type: User
Company: Institute of Cancer Research and Imperial College London
Bio: PhD candidate at the Institute of Cancer Research and Imperial College London. Working on geometric deep learning applied to cancer biology.
Twitter: devriesmatt
Location: London
Blog: https://devriesmatt.github.io
Matt De Vries's Projects
Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks. High-accuracy medical retina (eye) image segmentation.
The Unified Machine Learning Framework
Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning
Mathematics of Deep Learning, Courant Insititute, Spring 19
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Latex template for the MIDL Conference
Inherently Interpretable Time Series Classification via Multiple Instance Learning (MILLET)
rendering (optionally temporal) point clouds using Mitsuba2
Python loading/manipulation functions for modelnet datasets
A repository containing the projects from my MSc. in Artificial Intelligence from the University of Southampton
A set of small programs and scripts to convert OBJ 3D file into vox space and then import it into python as an np array
This repository contains the code for the ICCV 2019 paper "Occupancy Flow - 4D Reconstruction by Learning Particle Dynamics"
Implementation of the "Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos" paper.
Personal WebSite built using Jekyll and GitHub pages
This is a simple script for rendering point clouds using mitsuba2.
(ICLR 2022 poster) Official PyTorch implementation of "Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework"
PyTorch implementation of Pointnet2/Pointnet++ which compilation issues have been resolved
PyTorch reimplementation for "PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors" https://arxiv.org/abs/1808.10322
http://clesperanto.net
Pytorch implementation of the Graph Attention Network model by Veliฤkoviฤ et. al (2017, https://arxiv.org/abs/1710.10903)