OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Atlasnet

AtlasNet is an open-source Python research implementation of a learned 3D surface-generation network that synthesizes mesh geometry and connectivity from a low-resolution point cloud or an image.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Atlasnet — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you need research code for experimenting with learned mesh generation from point clouds or images and can set up the documented development environment.

Who it is for

  • Computer-vision and 3D-geometry researchers exploring surface generation.
  • Developers prototyping point-cloud-to-mesh or image-to-3D reconstruction workflows.

Documented uses

  • Generate a 3D mesh from a low-resolution point cloud.
  • Reconstruct a mesh from an image.
  • Explore or train 3D surface-generation models using the repository's demo and ShapeNet training paths.
Before you choose

Requirements & limits

The source repository is public and specifies an MIT license.

  • The README specifies Python 3.6, PyTorch 1.7.1, torchvision 0.8.2 and cudatoolkit 10.1, with PyMesh also listed as an implementation dependency.
  • The repository documents separate demo and ShapeNet training paths.
  • Data retrieval may require manual download if automatic download fails.
  • Chamfer and Metro distance components are described as optional; the README identifies Metro as GPL-3 licensed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the AtlasNet research environment

Prepare the repository and install its listed Python and PyTorch dependencies.

Before you start

  • Python 3.6
  • Conda
  • PyTorch 1.7.1, torchvision 0.8.2 and cudatoolkit 10.1
  • Repository requirements installed with pip

Steps

  1. Clone the repository with its submodules and change into the AtlasNet directory.

  2. Create and activate a Conda environment using Python 3.6.

  3. Install the listed PyTorch, torchvision and cudatoolkit versions.

  4. Install the repository's pip requirements file.

Expected outcome

The documented Python environment and repository dependencies are installed; the README lists separate demo and training instructions as the next stage.

Guide limitations

  • This setup guide does not cover running the demo or training.
  • The README lists PyMesh and CUDA 10.1 among the implementation requirements.
  • The README says data may need to be downloaded manually if automatic retrieval fails.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
ThibaultGROUEIX/AtlasNet · Official homepage title · retained in its source language
How we review sourcesSuggest a correction