Open3D: A Modern Library for 3D Data Processing
arXiv:1801.09847
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
Cited by in corpus (58)
- A comprehensive survey on point cloud registration
- Deep Closest Point: Learning Representations for Point Cloud Registration
- HoloLens 2 Research Mode as a Tool for Computer Vision Research
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation
- Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)
- Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter
- gradSim: Differentiable simulation for system identification and visuomotor control
- EyeNeRF: A Hybrid Representation for Photorealistic Synthesis, Animation and Relighting of Human Eyes
- Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity
- AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
- Eiffel Tower: A Deep-Sea Underwater Dataset for Long-Term Visual Localization
- Robust Point Cloud Registration Framework Based on Deep Graph Matching
- CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps
- 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
- 6D Object Pose Regression via Supervised Learning on Point Clouds
- Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration
- RF-Annotate: Automatic RF-Supervised Image Annotation of Common Objects in Context
- Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
- A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
- Efficient and Accurate Candidate Generation for Grasp Pose Detection in SE(3)
- Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of Freedom
- 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
- Shape As Points: A Differentiable Poisson Solver
- Elastic Interaction of Particles for Robotic Tactile Simulation
- 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
- Learning Transformation Synchronization
- Riggable 3D Face Reconstruction via In-Network Optimization
- Creating a Large-scale Synthetic Dataset for Human Activity Recognition
- DFC: Deep Feature Consistency for Robust Point Cloud Registration
- Tabletop Object Rearrangement: Team ACRV's Entry to OCRTOC
- Towards Affordance Prediction with Vision via Task Oriented Grasp Quality Metrics
- Compositional Scalable Object SLAM
- Elastic Tactile Simulation Towards Tactile-Visual Perception
- EnforceNet: Monocular Camera Localization in Large Scale Indoor Sparse LiDAR Point Cloud
- Duodepth: Static Gesture Recognition Via Dual Depth Sensors
- Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
- 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
- GSECnet: Ground Segmentation of Point Clouds for Edge Computing
- Mirror3D: Depth Refinement for Mirror Surfaces
- Self-supervised Geometric Perception
- Plane Pair Matching for Efficient 3D View Registration
- Stable Object Reorientation using Contact Plane Registration
- A Method to Generate High Precision Mesh Model and RGB-D Datasetfor 6D Pose Estimation Task
- 3D Modeling and WebVR Implementation using Azure Kinect, Open3D, and Three.js
- A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras
- Registration Loss Learning for Deep Probabilistic Point Set Registration
- What Do Single-view 3D Reconstruction Networks Learn?
- Where to Explore Next? ExHistCNN for History-aware Autonomous 3D Exploration
- Multi-Pen Robust Robotic 3D Drawing Using Closed-Loop Planning
- Fit to Measure: Reasoning about Sizes for Robust Object Recognition
- The Power of Points for Modeling Humans in Clothing
- Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
- Learning to Design and Construct Bridge without Blueprint
- BIDCD -- Bosch Industrial Depth Completion Dataset
- Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
- 3D Registration for Self-Occluded Objects in Context