Skip to Main content Skip to Navigation
Conference papers

Torch-Points3D: A modular multi-task framework for reproducible deep learning on 3D point clouds

Abstract : We introduce Torch-Points3D, an open-source framework designed to facilitate the use of deep networks on 3D 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03013190
Contributor : Loic Landrieu Connect in order to contact the contributor
Submitted on : Wednesday, November 18, 2020 - 7:52:38 PM
Last modification on : Wednesday, November 17, 2021 - 12:31:09 PM
Long-term archiving on: : Friday, February 19, 2021 - 8:50:29 PM

File

2010.04642.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03013190, version 1

Citation

Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu. Torch-Points3D: A modular multi-task framework for reproducible deep learning on 3D point clouds. 3DV 2020 - International Conference on 3D Vision, Nov 2020, online, Japan. ⟨hal-03013190⟩

Share

Metrics

Record views

124

Files downloads

700