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

Thomas Chaton , Nicolas Chaulet (1) , Sofiane Horache (2) , Loic Landrieu (3)

1 Principia Labs
2 CAOR - Centre de Robotique
3 LaSTIG - Laboratoire sciences et technologies de l'information géographique

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.

Domaines: Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

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⟩