Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds

Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu
10/9/2020
cs.CVcs.AIstat.ML

Official code: nicolas-chaulet/torch-points3d (269 stars, last commit 2021-12-10).

Abstract

We introduce Torch-Points3D, an open-source framework designed to facilitate the use of deep networks on3D data. Its modular design, efficient implementation, and user-friendly interfaces make it a relevant tool for research and productization alike. Beyond multiple quality-of-life features, our goal is to standardize a higher level of transparency and reproducibility in 3D deep learning research, and to lower its barrier to entry. In this paper, we present the design principles of Torch-Points3D, as well as extensive benchmarks of multiple state-of-the-art algorithms and inference schemes across several datasets and tasks. The modularity of Torch-Points3D allows us to design fair and rigorous experimental protocols in which all methods are evaluated in the same conditions. The Torch-Points3D repository :https://github.com/nicolas-chaulet/torch-points3d

View on arXivView PDF

Code Implementations(1)

nicolas-chaulet/torch-points3dOfficial100%

Pytorch framework for doing deep learning on point clouds.

26949Shell, PythonJan 9, 20224 years agoNOASSERTION

Similar Papers

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

82% match1 repo2.9k2019

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

82% match1 repo198.9k2016

Multi-level Cellular Automata for FLIM networks

82% match2025

DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments

82% match1 repo332018

Combining Deep Learning with Good Old-Fashioned Machine Learning

82% match2022

LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks

82% match1 repo22024

Cite this paper

@article{chaton2020torchpointsd,
  title  = {Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds},
  author = {Thomas Chaton and Nicolas Chaulet and Sofiane Horache and Loic Landrieu},
  year   = {2020},
  eprint = {2010.04642},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2010.04642}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2010.04642.svg)](https://codeofpaper.com/paper/2010.04642)

Discussion