Open3D: A Modern Library for 3D Data Processing

Abstract

Open3D is an open-source library that supports rapid development of software that deals with 3D data. The Open3D frontend exposes a set of carefully selected data structures and algorithms in both C++ and Python. The backend is highly optimized and is set up for parallelization. Open3D was developed from a clean slate with a small and carefully considered set of dependencies. It can be set up on different platforms and compiled from source with minimal effort. The code is clean, consistently styled, and maintained via a clear code review mechanism. Open3D has been used in a number of published research projects and is actively deployed in the cloud. We welcome contributions from the open-source community.

http://www.open3d.org

References in corpus (1)

• TensorFlow: A system for large-scale machine learning

Cited by in corpus (159)

• RPM-Net: Robust Point Matching using Learned Features
• KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way
• Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
• Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data
• Unsupervised Scale-consistent Depth Learning from Video
• A comprehensive survey on point cloud registration
• Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic 3D laser scanning
• Range Image-based LiDAR Localization for Autonomous Vehicles
• Deep Closest Point: Learning Representations for Point Cloud Registration
• HoloLens 2 Research Mode as a Tool for Computer Vision Research
• Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
• Learning general and distinctive 3D local deep descriptors for point cloud registration
• Neural Dual Contouring
• R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method
• SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping
• Glass Segmentation with RGB-Thermal Image Pairs
• DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation
• Flightmare: A Flexible Quadrotor Simulator
• Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)
• Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter
• CherryPicker: Semantic Skeletonization and Topological Reconstruction of Cherry Trees
• gradSim: Differentiable simulation for system identification and visuomotor control
• Tangent Convolutions for Dense Prediction in 3D
• TEASER: Fast and Certifiable Point Cloud Registration
• K-VIL: Keypoints-based Visual Imitation Learning
• EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes
• Online Range Image-based Pole Extractor for Long-term LiDAR Localization in Urban Environments
• 3DMASC: Accessible, explainable 3D point clouds classification. Application to Bi-spectral Topo-bathymetric lidar data
• D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
• Reconstructing the Position and Intensity of Multiple Gamma-Ray Point Sources with a Sparse Parametric Algorithm
• Exploring Differential Geometry in Neural Implicits
• UVG-VPC: Voxelized Point Cloud Dataset for Visual Volumetric Video-based Coding
• DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration
• Multi-Features Guidance Network for partial-to-partial point cloud registration
• Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints
• cilantro: A Lean, Versatile, and Efficient Library for Point Cloud Data Processing
• Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity
• See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation
• AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
• You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
• Eiffel Tower: A Deep-Sea Underwater Dataset for Long-Term Visual Localization
• LightDepth: Single-View Depth Self-Supervision from Illumination Decline
• Learning to Grasp Clothing Structural Regions for Garment Manipulation Tasks
• SHREC 2021: Retrieval and classification of protein surfaces equipped with physical and chemical properties
• Simple But Effective Redundant Odometry for Autonomous Vehicles
• ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion
• Robust Point Cloud Registration Framework Based on Deep Graph Matching
• Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications
• GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model
• CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps
• Impact of color and mixing proportion of synthetic point clouds on semantic segmentation
• Incremental Multimodal Surface Mapping via Self-Organizing Gaussian Mixture Models
• Robust Partial-to-Partial Point Cloud Registration in a Full Range
• Automated spacing measurement of formwork system members with 3D point cloud data
• 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
• GraffMatch: Global Matching of 3D Lines and Planes for Wide Baseline LiDAR Registration
• MOT-DETR: 3D Single Shot Detection and Tracking with Transformers to build 3D representations for Agro-Food Robots
• Persistent Homology Meets Object Unity: Object Recognition in Clutter
• Deep Point Cloud Reconstruction
• Unseen Object Instance Segmentation for Robotic Environments
• Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration
• FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation Models
• 6D Object Pose Regression via Supervised Learning on Point Clouds
• Tac2Structure: Object Surface Reconstruction Only through Multi Times Touch
• Physical LiDAR Simulation in Real-Time Engine
• DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling
• ASH: A Modern Framework for Parallel Spatial Hashing in 3D Perception
• Points2Sound: From mono to binaural audio using 3D point cloud scenes
• 3D Atomic-Scale Metrology of Strain Relaxation and Roughness in Gate-All-Around (GAA) Transistors via Electron Ptychography
• Robust Hole-Detection in Triangular Meshes Irrespective of the Presence of Singular Vertices
• An Adaptive Graduated Nonconvexity Loss Function for Robust Nonlinear Least Squares Solutions
• Autonomous Marker-less Rapid Aerial Grasping
• Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping
• An approach to robust ICP initialization
• RF-Annotate: Automatic RF-Supervised Image Annotation of Common Objects in Context
• Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
• Efficient and Accurate Candidate Generation for Grasp Pose Detection in SE(3)
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
• Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of Freedom
• Combinatorial 3D Shape Generation via Sequential Assembly
• Object Finding in Cluttered Scenes Using Interactive Perception
• DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds
• Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations
• POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
• GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger
• Elastic Interaction of Particles for Robotic Tactile Simulation
• Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments
• Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
• Shape As Points: A Differentiable Poisson Solver
• ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants
• CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds
• PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
• Supersampling of Data from Structured-light Scanner with Deep Learning
• Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
• Generating 3D People in Scenes without People
• Creating a Large-scale Synthetic Dataset for Human Activity Recognition
• GenReg: Deep Generative Method for Fast Point Cloud Registration
• Future Urban Scenes Generation Through Vehicles Synthesis
• Riggable 3D Face Reconstruction via In-Network Optimization
• DFC: Deep Feature Consistency for Robust Point Cloud Registration
• Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics
• Toward Autonomous Robotic Micro-Suturing using Optical Coherence Tomography Calibration and Path Planning
• Learning Transformation Synchronization
• AI-supported Framework of Semi-Automatic Monoplotting for Monocular Oblique Visual Data Analysis
• Active search and coverage using point-cloud reinforcement learning
• A Modular Approach to the Embodiment of Hand Motions from Human Demonstrations
• NormalFlow: Fast, Robust, and Accurate Contact-based Object 6DoF Pose Tracking with Vision-based Tactile Sensors
• Learning Localization of Body and Finger Animation Skeleton Joints on Three-Dimensional Models of Human Bodies
• CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
• Enriching thermal point clouds of buildings using semantic 3D building models
• Elastic Tactile Simulation Towards Tactile-Visual Perception
• EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud
• Compositional Scalable Object SLAM
• Tabletop Object Rearrangement: Team ACRV's Entry to OCRTOC
• Duodepth: Static Gesture Recognition Via Dual Depth Sensors
• Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics
• Visual-Inertial Object Detection and Mapping
• SENSAAS (SENsitive Surface As A Shape): utilizing open-source algorithms for 3D point cloud alignment of molecules
• Bayesian Optimization with Approximate Set Kernels
• Taking a Deeper Look at the Inverse Compositional Algorithm
• 3D Freehand Ultrasound using Visual Inertial and Deep Inertial Odometry for Measuring Patellar Tracking
• Neural Mesh Refiner for 6-DoF Pose Estimation
• Simulated LiDAR Repositioning: a novel point cloud data augmentation method
• Self-supervised Geometric Perception
• GSECnet: Ground Segmentation of Point Clouds for Edge Computing
• CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map
• Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
• A Method to Generate High Precision Mesh Model and RGB-D Datasetfor 6D Pose Estimation Task
• Stable Object Reorientation using Contact Plane Registration
• Mirror3D: Depth Refinement for Mirror Surfaces
• A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras
• Adversarial point set registration
• Plane Pair Matching for Efficient 3D View Registration
• PointMixer: MLP-Mixer for Point Cloud Understanding
• Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation
• 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
• 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
• 3D Modeling and WebVR Implementation using Azure Kinect, Open3D, and Three.js
• The Power of Points for Modeling Humans in Clothing
• Fit to Measure: Reasoning about Sizes for Robust Object Recognition
• Long-Term Visual Localization in Dynamic Benthic Environments: A Dataset, Footprint-Based Ground Truth, and Visual Place Recognition Benchmark
• 3D Surface Reconstruction by Pointillism
• Registration Loss Learning for Deep Probabilistic Point Set Registration
• Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
• 3D Registration for Self-Occluded Objects in Context
• Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints
• Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration
• Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
• RIN: Textured Human Model Recovery and Imitation with a Single Image
• Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
• What Do Single-view 3D Reconstruction Networks Learn?
• Pull-back Geometry of Persistent Homology Encodings
• Multi-Pen Robust Robotic 3D Drawing Using Closed-Loop Planning
• L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasets
• Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
• Boxhead: A Dataset for Learning Hierarchical Representations
• 3D Annotation Of Arbitrary Objects In The Wild
• BIDCD -- Bosch Industrial Depth Completion Dataset
• Learning to Design and Construct Bridge without Blueprint