Gauge equivariant mesh cnn

Overview

Geometric Mesh CNN

The code in this repository is an implementation of the Gauge Equivariant Mesh CNN introduced in the paper Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphsDownload PDF by Pim de Haan, Maurice Weiler, Taco Cohen and Max Welling, presented at ICLR 2021.

We would like to thank Ruben Wiersma as his implementation of Harmonic Surface Networks served as an inspiration for some parts of the code. Furthermore, we would like to thank Julian Suk for beta-testing the code.

Installation & dependencies

Make sure the following dependencies are installed:

  • Python (tested on 3.8)
  • Pytorch (tested on 1.8)
  • Pytorch Geometric (tested on 1.6.3)
  • Conda

Then to install, clone this repository and install the gem_cnn package by executing in this directory:

pip install .

Docker

Alternatively, if you have a GPU with CUDA 11.1 and have set up docker, then you can easily run the experiment at experiments/shapes.py in the following way:.

To build the image run in this directory:

docker build . -t gem_cnn_demo

Then to run:

docker run -it --rm --runtime=nvidia gem_cnn_demo python experiments/shapes.py

In order to run the FAUST experiments via Docker, we recommend mounting the local data folder inside the docker container by running:

docker run -it --rm --runtime=nvidia -v $(pwd)/data:/workspace/data gem_cnn_demo python experiments/faust_direct.py

Then run once, and follow instructions on how to download the dataset. Then run again to train the FAUST model.

Usage

The code implements a graph convolution with Pytorch Geometric.

Example experiments

In the folder experiments, the following examples are given:

  • experiments/shapes.py a simple toy experiment to classify geometric shapes.
  • experiments/faust_direct.py an implementation of a network similar the network used in our paper on the FAUST dataset. It does message passing directly over the edges of the mesh and does not use pooling. The used input features are the non-equivariant XYZ coordinates.
  • experiments/faust_pool.py is an alternative implementation for FAUST. It uses convolution over larger distances than direct neighbours, pooling and the equivariant matrix features.

All example experiments use Pytorch-Ignite, but the GEM-CNN code does not depend on this.

Reference

If you find our work useful, please cite

@inproceedings{dehaan2021,  
  title={Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs},  
  author={Pim de Haan and Maurice Weiler and Taco Cohen and Max Welling}
  booktitle={International Conference on Learning Representations},  
  year={2021},  
  url={https://openreview.net/forum?id=Jnspzp-oIZE}  
}

Export

This software may be subject to U.S. and international export, re-export, or transfer (“export”) laws. Diversion contrary to U.S. and international law is strictly prohibited.

Owner
An initiative of Qualcomm Technologies, Inc.
Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation This is the implementation of the approach describ

Taosha Fan 47 Nov 15, 2022
Evaluation suite for large-scale language models.

This repo contains code for running the evaluations and reproducing the results from the Jurassic-1 Technical Paper (see blog post), with current support for running the tasks through both the AI21 S

71 Dec 17, 2022
Generative Art Using Neural Visual Grammars and Dual Encoders

Generative Art Using Neural Visual Grammars and Dual Encoders Arnheim 1 The original algorithm from the paper Generative Art Using Neural Visual Gramm

DeepMind 231 Jan 05, 2023
A python code to convert Keras pre-trained weights to Pytorch version

Weights_Keras_2_Pytorch 最近想在Pytorch项目里使用一下谷歌的NIMA,但是发现没有预训练好的pytorch权重,于是整理了一下将Keras预训练权重转为Pytorch的代码,目前是支持Keras的Conv2D, Dense, DepthwiseConv2D, Batch

Liu Hengyu 2 Dec 16, 2021
💡 Type hints for Numpy

Type hints with dynamic checks for Numpy! (❒) Installation pip install nptyping (❒) Usage (❒) NDArray nptyping.NDArray lets you define the shape and

Ramon Hagenaars 377 Dec 28, 2022
A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Simple implementation of Equivariant GNN A short implementation of E(n) Equivariant Graph Neural Networks for HOMO energy prediction. Just 50 lines of

Arsenii Senya Ashukha 97 Dec 23, 2022
Code for Understanding Pooling in Graph Neural Networks

Select, Reduce, Connect This repository contains the code used for the experiments of: "Understanding Pooling in Graph Neural Networks" Setup Install

Daniele Grattarola 37 Dec 13, 2022
Unet network with mean teacher for altrasound image segmentation

Unet network with mean teacher for altrasound image segmentation

5 Nov 21, 2022
Multi-Scale Geometric Consistency Guided Multi-View Stereo

ACMM [News] The code for ACMH is released!!! [News] The code for ACMP is released!!! About ACMM is a multi-scale geometric consistency guided multi-vi

Qingshan Xu 118 Jan 04, 2023
Estimating Example Difficulty using Variance of Gradients

Estimating Example Difficulty using Variance of Gradients This repository contains source code necessary to reproduce some of the main results in the

Chirag Agarwal 48 Dec 26, 2022
RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation

RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation Anonymous submission Abstract 3D obj

30 Sep 16, 2022
The source code and dataset for the RecGURU paper (WSDM 2022)

RecGURU About The Project Source code and baselines for the RecGURU paper "RecGURU: Adversarial Learning of Generalized User Representations for Cross

Chenglin Li 17 Jan 07, 2023
A facial recognition doorbell system using a Raspberry Pi

Facial Recognition Doorbell This project expands on the person-detecting doorbell system to allow it to identify faces, and announce names accordingly

rydercalmdown 22 Apr 15, 2022
Official code for paper "ISNet: Costless and Implicit Image Segmentation for Deep Classifiers, with Application in COVID-19 Detection"

Official code for paper "ISNet: Costless and Implicit Image Segmentation for Deep Classifiers, with Application in COVID-19 Detection". LRPDenseNet.py

Pedro Ricardo Ariel Salvador Bassi 2 Sep 21, 2022
Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

pytorch Implementation of U-Net, R2U-Net, Attention U-Net, Attention R2U-Net U-Net: Convolutional Networks for Biomedical Image Segmentation https://a

leejunhyun 2k Jan 02, 2023
A project which aims to protect your privacy using inexpensive hardware and easily modifiable software

Protecting your privacy using an ESP32, an IR sensor and a python script This project, which I personally call the "never-gonna-catch-me-in-the-act-ev

8 Oct 10, 2022
Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh

Arjun Majumdar 44 Dec 14, 2022
HybVIO visual-inertial odometry and SLAM system

HybVIO A visual-inertial odometry system with an optional SLAM module. This is a research-oriented codebase, which has been published for the purposes

Spectacular AI 320 Jan 03, 2023
ConvMixer unofficial implementation

ConvMixer ConvMixer 非官方实现 pytorch 版本已经实现。 nets 是重构版本 ,test 是官方代码 感兴趣小伙伴可以对照看一下。 keras 已经实现 tf2.x 中 是tensorflow 2 版本 gelu 激活函数要求 tf=2.4 否则使用入下代码代替gelu

Jian Tengfei 8 Jul 11, 2022
Official implementation of "Dynamic Anchor Learning for Arbitrary-Oriented Object Detection" (AAAI2021).

DAL This project hosts the official implementation for our AAAI 2021 paper: Dynamic Anchor Learning for Arbitrary-Oriented Object Detection [arxiv] [c

ming71 215 Nov 28, 2022