This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.
Alternatives To Atlasnet
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
19 hours ago64September 20, 2022141otherGo
Netmaker makes networks with WireGuard. Netmaker automates fast, secure, and distributed virtual networks.
Mosn4,1582a day ago91August 23, 2022265apache-2.0Go
The Cloud-Native Network Proxy Platform
5 days ago186otherC++
CloudCompare main repository
2 days ago261agpl-3.0C++
open Multi-View Stereo reconstruction library
Coolstore Microservices2,215
3 months ago25mitC#
A full-stack .NET microservices build on Dapr and Tye
2 days ago67mitC++
A C++ & Python viewer for 3D data like meshes and point clouds
19 days ago8gpl-3.0C++
A lightweight, easy-to-use, and efficient C++ library for processing and rendering 3D data
Point Cloud Utils835
16 days ago29December 13, 202115gpl-2.0C++
A Python library for common tasks on 3D point clouds
7 months ago11mitPython
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.
21 hours ago107apache-2.0JavaScript
Layer5, expect more from your infrastructure
Alternatives To Atlasnet
Select To Compare

Alternative Project Comparisons

AtlasNet [Project Page] [Paper] [Talk]

AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
Thibault Groueix, Matthew Fisher, Vladimir G. Kim , Bryan C. Russell, Mathieu Aubry
In CVPR, 2018.

🚀 New branch : AtlasNet + Shape Reconstruction by Learning Differentiable Surface Representations

chair.png chair.gif


This implementation uses Python 3.6, Pytorch, Pymesh, Cuda 10.1.

# Copy/Paste the snippet in a terminal
git clone --recurse-submodules
cd AtlasNet 

conda create -n atlasnet python=3.6 --yes
conda activate atlasnet
conda install pytorch==1.7.1 torchvision==0.8.2 cudatoolkit=10.1 -c pytorch --yes
pip install --user --requirement  requirements.txt # pip dependencies
Optional : Compile Chamfer (MIT) + Metro Distance (GPL3 Licence)
# Copy/Paste the snippet in a terminal
python auxiliary/ChamferDistancePytorch/chamfer3D/ install #MIT
cd auxiliary
git clone
cd metro_sources; python --build # build metro distance #GPL3
cd ../..

A note on data.

Data download should be automatic. However, due to the new google drive traffic caps, you may have to download manually. If you run into an error running the demo, you can refer to #61.

You can manually download the data from three sources (there are the same) :

Please make sure to unzip the archives in the right places :

cd AtlasNet
mkdir data
unzip -d ./data/
unzip -d ./data/
unzip -d ./data/
unzip -d ./training/


  • Demo : python --demo
  • Training : python --shapenet13 Monitor on http://localhost:8890/
  • Latest Refacto 12-2019 - [x] Factorize Single View Reconstruction and autoencoder in same class
    - [x] Factorise Square and Sphere template in same class
    - [x] Add latent vector as bias after first layer(30% speedup)
    - [x] Remove last th in decoder
    - [x] Make large .pth tensor with all pointclouds in cache(drop the nasty Chunk_reader)
    - [x] Make-it multi-gpu
    - [x] Add netvision visualization of the results
    - [x] Rewrite main script object-oriented
    - [x] Check that everything works in latest pytorch version
    - [x] Add more layer by default and flag for the number of layers and hidden neurons
    - [x] Add a flag to generate a mesh directly
    - [x] Add a python setup install
    - [x] Make sure GPU are used at 100%
    - [x] Add f-score in Chamfer + report f-score
    - [x] Get rid of shapenet_v2 data and use v1!
    - [x] Fix path issues no more sys.path.append
    - [x] Preprocess shapenet 55 and add it in dataloader
    - [x] Make minimal dependencies

Quantitative Results

Method Chamfer (*1) Fscore (*2) Metro (*3) Total Train time (min)
Autoencoder 25 Squares 1.35 82.3% 6.82 731
Autoencoder 1 Sphere 1.35 83.3% 6.94 548
SingleView 25 Squares 3.78 63.1% 8.94 1422
SingleView 1 Sphere 3.76 64.4% 9.01 1297
  • (*1) x1000. Computed between 2500 ground truth points and 2500 reconstructed points.
  • (*2) The threshold is 0.001
  • (*3) x100. Metro is ran on unormalized point clouds (which explains a difference with the paper's numbers)

Related projects

Citing this work

          title={{AtlasNet: A Papier-M\^ach\'e Approach to Learning 3D Surface Generation}},
          author={Groueix, Thibault and Fisher, Matthew and Kim, Vladimir G. and Russell, Bryan and Aubry, Mathieu},
          booktitle={Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},

Popular Mesh Projects
Popular Cloud Computing Projects
Popular Graphics Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Cloud Computing
3d Graphics
Computer Vision
Geometry Processing