Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds
This framework addresses reproducibility and accessibility issues for researchers and practitioners working with 3D point cloud data, though it is incremental as it builds on existing tools.
The authors introduced Torch-Points3D, an open-source modular framework to standardize reproducibility and lower barriers in 3D deep learning research, benchmarking multiple state-of-the-art algorithms across datasets and tasks under fair conditions.
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