Top 217 point-cloud open source projects

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018

Multi-threaded and SSE friendly NDT algorithm

Autoencoder for Point Clouds

A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷

A Python library for common tasks on 3D point clouds

KITTI data processing and 3D CNN for Vehicle Detection

Implementation of the KinectFusion approach in modern C++14 and CUDA

SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)

Pure Numpy Implementation of the Coherent Point Drift Algorithm

pytorch implementation of >>Patch-base progressive 3D Point Set Upsampling<<

PyTorch Code of our WACV2020 paper: Silhouette Guided Point Cloud Reconstruction beyond Occlusion

converts set of point clouds to a video using three.js

PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"

iPhone X -> Unity VFX Graph demo (real-time Point Cloud streaming)

A port of the Point Cloud Library (PCL) using Java Native Interface (JNI).

A New 3D Detector. Code Will be made public.

A pointnet++ fork, with focus on semantic segmentation of differents datasets

Implementation of the iterative closest point algorithm. A point cloud is transformed such that it best matches a reference point cloud.

A clean PointNet++ segmentation model implementation. Support batch of samples with different number of points.

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Learning low-shot object classification with explicit shape bias learned from point clouds

Las Vegas Reconstruction 2.0

😎 Awesome LIDAR list. The list includes LIDAR manufacturers, datasets, point cloud-processing algorithms, point cloud frameworks and simulators.

Single shape Deep Point Cloud Consolidation [TOG 2021]

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)

Real-time LIDAR-based Urban Road and Sidewalk detection for Autonomous Vehicles 🚗

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Augmentation package for 3d data based on albumentaitons

Official implementation of "Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis", ICCV 2021

Point Cloud Compression used in i3s Scene Layer Format

Algorithm that converts point cloud data into an occupancy grid

Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)

Code base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

Official Python/PyTorch Implementation for "All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds"

Extension of RealSense Unity Wrapper [Unofficial]

Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks

Pytorch framework for doing deep learning on point clouds.

This is a costmap plugin for costmap_2d pkg. This plugin supports multiple depth cameras and run in real time.

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

Rust algorithms for isosurface extraction

Code for "CMRNet: Camera to LiDAR-Map Registration" (ITSC 2019) - WIP

MinkLoc3D: Point Cloud Based Large-Scale Place Recognition

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network

This is the official repository of the open-source Open Infra Platform software (as of April 2020).

Learning Convolutional Transforms for Point Cloud Geometry Compression

The PyTorch Implementation of F-ConvNet for 3D Object Detection

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis, ICCV 2019, Seoul, Korea

Official PyTorch code for the paper: "Point-Based Modeling of Human Clothing" (ICCV 2021)

Efficient Online Transfer Learning for 3D Object Detection in Autonomous Driving

Creating real-time dynamic Point Clouds using PyQtGraph, Kinect 2 and the python library PyKinect2.

Improved Deep Point Cloud Geometry Compression

Stream openni2 depth images over the network

A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm

SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification - ECCV 2020 oral

Fast Descriptors and Correspondence Propagation for Robust Global Point Cloud Registration

ROS 2 wrapper beta for the ZED SDK

CVPR 2020 papers focusing on point cloud analysis

[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory