Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds
Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/nicolas-chaulet/torch-points3dOfficialIn paperpytorch★ 263
- github.com/nicolas-chaulet/deeppointcloud-benchmarkspytorch★ 2,695
- github.com/idegelis/torch-points3d-dc3dcdpytorch★ 17
- github.com/IdeGelis/torch-points3d-SiamKPConvVariantspytorch★ 13
- github.com/idegelis/torch-points3d-ssl-dcvapytorch★ 8
- github.com/umrlastig/torch-points3dpytorch★ 3
- github.com/llei66/torch3d-deepcroppytorch★ 1
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