NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

Overview

NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

This repository provides our implementation of the CVPR 2021 paper NeuroMorph. Our algorithm produces in one go, i.e., in a single feed forward pass, a smooth interpolation and point-to-point correspondences between two input 3D shapes. It is learned in a self-supervised manner from an unlabelled collection of deformable and heterogeneous shapes.

If you use our work, please cite:

@inproceedings{eisenberger2021neuromorph, 
  title={NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go}, 
  author={Eisenberger, Marvin and Novotny, David and Kerchenbaum, Gael and Labatut, Patrick and Neverova, Natalia and Cremers, Daniel and Vedaldi, Andrea}, 
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, 
  pages={7473--7483}, 
  year={2021}
}

Requirements

The code was tested on Python 3.8.10 with the PyTorch version 1.9.1 and CUDA 10.2. The code also requires the pytorch-geometric library (installation instructions) and matplotlib. Finally, MATLAB with the Statistics and Machine Learning Toolbox is used to pre-process ceratin datasets (we tested MATLAB versions 2019b and 2021b). The code should run on Linux, macOS and Windows.

Installing NeuroMorph

Using Anaconda, you can install the required dependencies as follows:

conda create -n neuromorph python=3.8
conda activate neuromorph
conda install pytorch cudatoolkit=10.2 -c pytorch
conda install matplotlib
conda install pyg -c pyg -c conda-forge

Running NeuroMorph

In order to run NeuroMorph:

  • Specify the location of datasets on your device under data_folder_ in param.py.
  • To use your own data, create a new dataset in data/data.py.
  • To train FAUST remeshed, run the main script main_train.py. Modify the script as needed to train on different data.

For a more detailed tutorial, see the next section.

Reproducing the experiments

We show below how to reproduce the experiments on the FAUST remeshed data.

Data download

You can download experimental mesh data from here from the authors of the Deep Geometric Functional Maps. Download the FAUST_r.zip file from this site, unzip it, and move the content of the directory to /data/mesh/FAUST_r .

Data preprocessing

Meshes must be subsampled and remeshed (for data augmentation during training) and geodesic distance matrices must be computed before the learning code runs. For this, we use the data_preprocessing/preprocess_dataset.m MATLAB scripts (we tested V2019b and V2021b).

Start MATLAB and do the following:

cd 
   
    /data_preprocessing
   
preprocess_dataset("../data/meshes/FAUST_r/", ".off")

The result should be a list of MATLAB mesh files in a mat subfolder (e.g., data/meshes/FAUST_r/mat ), plus additional data.

Model training

If you stored the data in the directory given above, you can train the model by running:

mkdir -p data/{checkpoint,out}
python main_train.py

The trained models will be saved in a series of checkpoints at /data/out/ . Otherwise, edit param.py to change the paths.

Model testing

Upon completion, evaluate the trained model with main_test.py . Specify the checkpoint folder name by running:

python main_test.py <TIME_STAMP_FAUST>

Here is any of the directories saved in /data/out/ . This automatically saves correspondences and interpolations on the FAUST remeshed test set to /data/out/ . For reference, on FAUST you should expect a validation error around 0.25 after 400 epochs.

Contributing

See the CONTRIBUTING file for how to help out.

License

NeuroMorph is MIT licensed, as described in the LICENSE file. NeuroMorph includes a few files from other open source projects, as further detailed in the same LICENSE file.

Owner
Meta Research
Meta Research
[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

[Project] [PDF] This repository contains code for our SIGGRAPH'22 paper "StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets" by Axel Sauer, Katja

742 Jan 04, 2023
Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation (CoRL 2021)

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation [Project website] [Paper] This project is a PyTorch i

Cognitive Learning for Vision and Robotics (CLVR) lab @ USC 6 Feb 28, 2022
Hummingbird compiles trained ML models into tensor computation for faster inference.

Hummingbird Introduction Hummingbird is a library for compiling trained traditional ML models into tensor computations. Hummingbird allows users to se

Microsoft 3.1k Dec 30, 2022
Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu,

GEMS Lab: Graph Exploration & Mining at Scale, University of Michigan 70 Dec 18, 2022
General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends)

General purpose GPU compute framework for cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usec

The Kompute Project 1k Jan 06, 2023
Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

Skeleton Merger Skeleton Merger, an Unsupervised Aligned Keypoint Detector. The paper is available at https://arxiv.org/abs/2103.10814. A map of the r

北海若 48 Nov 14, 2022
Advantage Actor Critic (A2C): jax + flax implementation

Advantage Actor Critic (A2C): jax + flax implementation Current version supports only environments with continious action spaces and was tested on muj

Andrey 3 Jan 23, 2022
Learning to Self-Train for Semi-Supervised Few-Shot

Learning to Self-Train for Semi-Supervised Few-Shot Classification This repository contains the TensorFlow implementation for NeurIPS 2019 Paper "Lear

86 Dec 29, 2022
[ECCV 2020] Gradient-Induced Co-Saliency Detection

Gradient-Induced Co-Saliency Detection Zhao Zhang*, Wenda Jin*, Jun Xu, Ming-Ming Cheng ⭐ Project Home » The official repo of the ECCV 2020 paper Grad

Zhao Zhang 35 Nov 25, 2022
Wanli Li and Tieyun Qian: Exploit a Multi-head Reference Graph for Semi-supervised Relation Extraction, IJCNN 2021

MRefG Wanli Li and Tieyun Qian: "Exploit a Multi-head Reference Graph for Semi-supervised Relation Extraction", IJCNN 2021 1. Requirements To reproduc

万理 5 Jul 26, 2022
Data-depth-inference - Data depth inference with python

Welcome! This readme will guide you through the use of the code in this reposito

Marco 3 Feb 08, 2022
TensorLight - A high-level framework for TensorFlow

TensorLight is a high-level framework for TensorFlow-based machine intelligence applications. It reduces boilerplate code and enables advanced feature

Benjamin Kan 10 Jul 31, 2022
PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

Improving Visual-Semantic Embeddings with Hard Negatives Code for the image-caption retrieval methods from VSE++: Improving Visual-Semantic Embeddings

Fartash Faghri 441 Dec 05, 2022
Robotics environments

Robotics environments Details and documentation on these robotics environments are available in OpenAI's blog post and the accompanying technical repo

Farama Foundation 121 Dec 28, 2022
The implementation code for "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction"

DAGAN This is the official implementation code for DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruct

TensorLayer Community 159 Nov 22, 2022
Official implementation for Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020

Likelihood-Regret Official implementation of Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020. T

Xavier 33 Oct 12, 2022
PyTorch implementation of DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images

DARDet PyTorch implementation of "DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images", [pdf]. Highlights: 1. We develop a new dense

41 Oct 23, 2022
ToFFi - Toolbox for Frequency-based Fingerprinting of Brain Signals

ToFFi Toolbox This repository contains "before peer review" version of the software related to the preprint of the publication ToFFi - Toolbox for Fre

4 Aug 31, 2022
A curated list of awesome projects and resources related fastai

A curated list of awesome projects and resources related fastai

Tanishq Abraham 138 Dec 22, 2022
[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

VITA 64 Dec 08, 2022