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

TL;DR

Torch-Points3D is an open-source, modular framework that standardizes and simplifies deep learning research on 3D point cloud data, enabling reproducibility and fair benchmarking across multiple tasks.

Contribution

It introduces a flexible, user-friendly framework that enhances transparency, reproducibility, and comparability in 3D deep learning research and applications.

Findings

Extensive benchmarks of state-of-the-art algorithms across datasets.

Demonstration of the framework's modularity for fair comparisons.

Improved reproducibility and standardization in 3D deep learning experiments.

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