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

arXiv: https://arxiv.org/abs/2010.04642 · HTML: https://mlsanity.com/paper/2010.04642/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [Efficient 3D Semantic Segmentation with Superpoint Transformer](https://mlsanity.com/paper/2306.08045/) (2023)
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://mlsanity.com/paper/2204.07548/) (2022)
- [On Representation Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2111.04964/) (2021)
- [Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping](https://mlsanity.com/paper/2111.11348/) (2021)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning](https://mlsanity.com/paper/2312.15084/) (2023)
- [Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering](https://mlsanity.com/paper/2401.06704/) (2024)
- [Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction](https://mlsanity.com/paper/2109.04398/) (2021)
- [Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass](https://mlsanity.com/paper/2112.11335/) (2021)
- [3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning](https://mlsanity.com/paper/2103.14533/) (2021)
- [A Review of Panoptic Segmentation for Mobile Mapping Point Clouds](https://mlsanity.com/paper/2304.13980/) (2023)
- [Towards accurate instance segmentation in large-scale LiDAR point clouds](https://mlsanity.com/paper/2307.02877/) (2023)
- [Representing Shape Collections with Alignment-Aware Linear Models](https://mlsanity.com/paper/2109.01605/) (2021)
- [Riedones3D: a celtic coin dataset for registration and fine-grained clustering](https://mlsanity.com/paper/2109.15033/) (2021)
- [Change detection needs change information: improving deep 3D point cloud change detection](https://mlsanity.com/paper/2304.12639/) (2023)
- [Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning](https://mlsanity.com/paper/2201.08051/) (2022)
- [EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation](https://mlsanity.com/paper/2512.00385/) (2025)
- [Effective Early Stopping of Point Cloud Neural Networks](https://mlsanity.com/paper/2209.15308/) (2022)
- [Semantic Segmentation of Urban Textured Meshes Through Point Sampling](https://mlsanity.com/paper/2302.10635/) (2023)
- [XFlow: Benchmarking Flow Behaviors over Graphs](https://mlsanity.com/paper/2308.03819/) (2023)
- [Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos](https://mlsanity.com/paper/2502.06543/) (2025)
- [A Unified Non-Parametric and Interpretable Point Cloud Analysis via t-FCW Graph Representation](https://mlsanity.com/paper/2605.15475/) (2026)

## Abstract (arXiv)

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