s3dis

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Pytorch framework for doing deep learning on point clouds.

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation

[CVPR 2022 Oral] SoftGroup for Instance Segmentation on 3D Point Clouds

[CVPR 2022 Oral] Official implementation for "Surface Representation for Point Clouds"

[ECCV2022] FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in "Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation"

Grid-GCN for Fast and Scalable Point Cloud Learning

[ICIP2023] TR3D: Towards Real-Time Indoor 3D Object Detection

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'

[WACV'24] TD3D: Top-Down Beats Bottom-Up in 3D Instance Segmentation

[AAAI2025] UniDet3D: Multi-dataset Indoor 3D Object Detection

CVPR 2020, "FPConv: Learning Local Flattening for Point Convolution"

PVT: Point-Voxel Transformer for 3D Deep Learning

[ICCV-23] Official implementation of SeedAL for seeding active learning for 3D semantic segmentation

[CVPR 2021] CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation

PyTorch implementation to train MortonNet and use it to compute point features. MortonNet is trained in a self-supervised fashion, and the features can be used for general tasks like part or semantic segmentation of point clouds.

A versatile framework for 3D machine learning built on Pytorch Lightning and Hydra [looking for contributors!]