轉自
A list of references on lidar point cloud processing for autonomous driving
LiDAR Pointcloud Clustering/Semantic Segmentation/Plane extraction
Tasks
: Road/Ground extraction, plane extraction, Semantic segmentation, open set instance segmentation, Clustering
Fast Segmentation of 3D Point Clouds: A Paradigm on LiDAR Data for Autonomous Vehicle Applications ICRA 2017 [
git
,
]
Time-series LIDAR Data Superimposition for Autonomous Driving [
]
Fast segmentation of 3D point clouds for ground vehicles [
ieee
]
An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells
Segmentation of Dynamic Objects from Laser Data [
]
A Fast Ground Segmentation Method for 3D Point Cloud [
]
Ground Estimation and Point Cloud Segmentation using SpatioTemporal Conditional Random Field [
]
Real-Time Road Segmentation Using LiDAR Data Processing on an FPGA [
]
Efficient Online Segmentation for Sparse 3D Laser Scans [
], [
git
]
CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data [
]
A Comparative Study of Segmentation and Classification Methods for 3D Point Clouds 2016 Masters Thesis [
]
Fast Multi-pass 3D Point Segmentation Based on a Structured Mesh Graph for Ground Vehicles
video
RangeNet++: Fast and Accurate LiDAR Semantic Segmentation [[link](
https://
github。com/PRBonn/lidar
-bonnetal
], [
]
Circular Convolutional Neural Networks for Panoramic Images and Laser Data
Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds [
]
Identifying Unknown Instances for Autonomous Driving/Open-set instance segmentation algorithm
CoRL 2019
[
]
RIU-Net: Embarrassingly simple semantic segmentation of3D LiDAR point cloud。 [
,
LU-net
]
SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving [
]
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation [
link
]
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation [
link
]
Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study IV 2020 [
]
Plane Segmentation Based on the Optimal-vector-field in LiDAR Point Clouds [
link
]
Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learning [
link
]
Learning Hierarchical Semantic Segmentations of LIDAR Data 3DV 2015 [
]
EfficientLPS: Efficient LiDAR Panoptic Segmentation 2021
,
video
4D Panoptic LiDAR Segmentation 2021 [
]
Pointcloud Density & Compression
DBSCAN : A density-based algorithm for discovering clusters in large spatial databases with noise (1996) [
]
Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection
Building Maps for Autonomous Navigation Using Sparse Visual SLAM Features [
]
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
Fast semantic segmentation of 3d point clounds with strongly varying density [
]
The Perfect Match: 3D Point Cloud Matching with Smoothed Densities [
,
code
]
Deep Compression for Dense Point Cloud Maps [
link
]
Improved Deep Point Cloud Geometry Compression [
,
git
]
Real-Time Spatio-Temporal LiDAR Point Cloud Compression [
]
Registration and Localization
A Review of Point Cloud Registration Algorithms for Mobile Robotics 2015 [
]
LOAM: Lidar Odometry and Mapping in Real-time RSS 2014 [
,
video
]
Fast Planar Surface 3D SLAM Using LIDAR 2016 [
]
Point Clouds Registration with Probabilistic Data Association IROS 2016 [
git
]
Robust LIDAR Localization using Multiresolution Gaussian Mixture Maps for Autonomous Driving IJRR 2017 [
], [
Thesis
]
Automatic Merging of Lidar Point-Clouds Using Data from Low-Cost GPS/IMU Systems SPIE 2011 [
]
Fast and Robust 3D Feature Extraction from Sparse Point Clouds [
]
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration [
]
Incremental Segment-Based Localization in 3D Point Clouds [
]
OverlapNet: Loop Closing for LiDAR-based SLAM, RSS 2020 [[pdf](OverlapNet: Loop Closing for LiDAR-based SLAM),
git
,
video
]
CorsNet: 3D Point Cloud Registration by Deep Neural Network, ICRA 2020 [
link
]
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis ICCV 2019 [
]
DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization [
,
project
,
video
]
Localisation using LiDAR and Camera Localisation in low visibility road conditions Master’s thesis 2017 [
]
Monocular Camera Localization in 3D LiDAR Maps IROS 2016 [
]
Feature Extraction
Fast Feature Detection and Stochastic Parameter Estimation of Road Shape using Multiple LIDAR [
]
Finding Planes in LiDAR Point Clouds for Real-Time Registration [
]
Online detection of planes in 2D lidar [
]
A Fast RANSAC–Based Registration Algorithm for Accurate Localization in Unknown Environments using LIDAR Measurements [
]
Hierarchical Plane Extraction (HPE): An Efficient Method For Extraction Of Planes From Large Pointcloud Datasets [
]
A Fast and Accurate Plane Detection Algorithm for Large Noisy Point Clouds Using Filtered Normals and Voxel Growing [
]
SPLATNet: Sparse Lattice Networks for Point Cloud Processing CVPR 2018 [
,
code
]
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding, 4D-VISION workshop at ECCV‘2020 [
,
workshop
]
Object detection and Tracking
Learning a Real-Time 3D Point Cloud Obstacle Discriminator via Bootstrapping
Terrain-Adaptive Obstacle Detection [
]
3D Object Detection from Roadside Data Using Laser Scanners [
]
3D Multiobject Tracking for Autonomous Driving : Masters thesis A S Abdul Rahman
Motion-based Detection and Tracking in 3D LiDAR Scans [
]
Lidar-histogram for fast road and obstacle detection [
]
End-to-end Learning of Multi-sensor 3D Tracking by Detection
Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection
Deep tracking in the wild: End-to-end tracking using recurrent neural networks [
]
Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection [
],
video
]
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection CVPR 2018 [
,
code
]
PIXOR: Real-time 3D Object Detection from Point Clouds CVPR 2018 [
]
Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges [
]
Low resolution lidar-based multi-object tracking for driving applications [
]
Patch Refinement —— Localized 3D Object Detection [
]
PointPillars: Fast Encoders for Object Detection from Point Clouds CVPR 2019 [
]
StarNet: Targeted Computation for Object Detection in Point Clouds NeurIPS 2019 ML4AD [
]
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection CVPR 2020 [
]
LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving CVPR 2019 [
]
Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection 2020 [
]
AFDet: Anchor Free One Stage 3D Object Detection [
]
SA-SSD: Structure Aware Single-stage 3D Object Detection from Point Cloud (CVPR 2020) [
,
git
]
Any Motion Detector: Learning Class-agnostic Scene Dynamics from a Sequence of LiDAR Point Clouds, ICRA 2020 [
]
MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views [
link
,
video
]
Learning to Optimally Segment Point Clouds, ICRA 2020 [
,
video
,
git
]
What You See is What You Get: Exploiting Visibility for 3D Object Detection [
,
video
,
project
]
Classification/Supervised Learning
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation [
link
,
link2
]
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
Improving LiDAR Point Cloud Classification using Intensities and Multiple Echoes [
]
DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet [
]
3D Object Localisation with Convolutional Neural Networks [
Thesis
]
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud [
]
PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud [
]
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks [
]
ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA [
]
Maps / Grids / HD Maps / Occupancy grids/ Prior Maps
Hierarchies of Octrees for Efficient 3D Mapping
Adaptive Resolution Grid Mapping using Nd-Tree [
ieee
], [
,
video
]
LIDAR-Data Accumulation Strategy To Generate High Definition Maps For Autonomous Vehicles [
link
]
Long-term robot mapping in dynamic environments, Aisha Naima Walcott Thesis MIT 2011 [
link
]
Long-term 3D map maintenance in dynamic environments ICRA 2014 [
,
video
]
Detection and Tracking of Moving Objects Using 2。5D Motion Grids ITSC 2015 [
]
Autonomous Vehicle Navigation in Rural Environments without Detailed Prior Maps ICRA 2018 [
,
video
]
3D Lidar-based Static and Moving Obstacle Detection in Driving Environments: an approach based on voxels and multi-region ground planes [
]
Spatio–Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments [
]
Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling [
]
Fast 3-D Urban Object Detection on Streaming Point Clouds [
]
Mobile Laser Scanned Point-Clouds for Road Object Detection and Extraction: A Review [
]
Efficient Continuous-time SLAM for 3D Lidar-based Online Mapping [
]
DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map [
],
video
]
Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Data [
]
HDNET: Exploiting HD Maps for 3D Object Detection [
]
Mapping with Dynamic-Object Probabilities Calculated from Single 3D Range Scans ICRA 2018 [
]
End-To-End Learning
Monocular Fisheye Camera Depth Estimation Using Semi-supervised Sparse Velodyne Data [
]
Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [
]
Simulated pointclouds / Simulators
Virtual Generation of Lidar Data for Autonomous Vehicles Simulation of a lidar sensor inside a virtual world Bachelors Thesis 2017
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving ACM 2018 [
]
Udacity based simulator [
link
,
git
]
Tutorial on Gazebo to simulate raycasting from Velodyne lidar [
link
]
Udacity Driving Dataset [
link
]
Virtual KITTI [
link
]
SynthCity: A large-scale synthetic point cloud 2019 [
dataset
,
]
Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perception [
link
]
Fast Synthetic LiDAR Rendering via Spherical UV Unwrapping of Equirectangular Z-Buffer Images 2020 [
]
Lidar Datasets
nuScenes : public large-scale dataset for autonomous driving [
dataset
]
nuScenes-lidarseg will be released in Q2 2020。 [
link
]
Ford Campus Vision and Lidar Data Set [
,
dataset
]
Oxford RobotCar dataset
dataset
1 Year, 1000km: The Oxford RobotCar Dataset
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively [
]
KAIST Complex Urban Data Set Dataset [
dataset
]
Semantic 3D 2017
dataset
Paris-Lille-3D: A Point Cloud Dataset for Urban Scene Segmentation and Classification [
dataset
]
Semantic KITTI 2019 [
dataset
]
A*3D: An Autonomous Driving Dataset in Challeging Environments [
dataset
],
video
]
HD Map Dataset & Localization Dataset NAVER Labs : [
link
]
Argoverse by ARGO AI : Two public datasets supported by highly detailed maps to test, experiment, and teach self-driving vehicles how to understand the world around them。 [
link
]
Lyft dataset [
link
]
SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances [
link
,
]
A2D2 Audi dataset [
link
]
PandaSet : Public large-scale dataset for autonomous driving provided by Hesai & Scale。 [
link
]
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways [
,
dataset
]
Spatio-Temporal, Movement, Flow estimation in Pointclouds
Rigid Scene Flow for 3D LiDAR Scans IROS 2016 [
]
Deep Lidar CNN to Understand the Dynamics of Moving Vehicles [
]
Learning motion field of LiDAR point cloud with convolutional networks [
link
]
Hallucinating Dense Optical Flow from Sparse Lidar for Autonomous Vehicles [
video
]
FlowNet3D: Learning Scene Flow in 3D Point Clouds CVPR 2019 [
,
code
]
LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images [
]
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks CVPR 2019 [
,
code
]
MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences, ICCV 2019 [
]
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR 2020 [
]
Advanced Topics/Other applications
Tasks
: Upsampling, Domain adaptation Sim2Real, NAS, SSL, shape reconstruction, outlier extraction, Compression, Change detection, Domain Transfer
Semantic Point Cloud Filtering, Masters thesis 2017
link
PU-GAN: a Point Cloud Upsampling Adversarial Network ICCV 2019 [
,
code
]
Neural Architecture Search for Object Detection in Point Cloud [
blog
], [
AutoDeepLabNAS paper
]
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space NeurIPS 2019 [
]
Domain Adaptation for Vehicle Detection from Bird’s Eye View LiDAR Point Cloud Data ICCVW 2019
Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imbalance [
]
Quantifying Data Augmentation for LiDAR based 3D Object Detection [
]
Improving 3D Object Detection through Progressive Population Based Augmentation [[pdf(
https://
arxiv。org/abs/2004。0083
1
)]
3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction VEHITS 2020 [
]
Training a Fast Object Detector for LiDAR Range Images Using Labeled Data from Sensors with Higher Resolution ITSC 2019 [
]
Performance of LiDAR object detection deep learning architectures based on artificially generated point cloud data from CARLA simulator 2019 [
]
PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation [
]
Efficient Learning on Point Clouds with Basis Point Sets ICCV 2019 [
]
Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds 2020 [
]
Neural Implicit Embedding for Point Cloud Analysis CVPR 2020 [
]
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation [
]
Mastering Data Complexity for Autonomous Driving with Adaptive Point Clouds for Urban Environments 2017 [
]
Visually aided changes detection in 3D lidar based reconstruction 2015 [
Thesis
]
Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks IROS 2020 [
,
video
]
Graphs and Pointclouds
Detection of closed sharp edges in point clouds using normal estimation and graph theory CAD 2007 [
link
]
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs CVPR 2017 [
,
vide
]
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs CVPR2018 [
]
ConvPoint: continuous convolutions for cloud processing Eurographics 3DOR, 2019 [
,
code
]
Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning [
CVPR Workshop 2019
],
video
Dynamic Graph CNN for Learning on Point Clouds [
,
project
] TOG 2019
Large-scale pointcloud Algorithms (vs scan based)
Deep Parametric Continuous Convolutional Neural Networks CVPR 2018 [
]
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space NeurIPS 2017 [
,
code
],
semantic seg code
Classification of Point Cloud for Road Scene Understanding with Multiscale Voxel Deep Network
Slides
Semantic Segmentation of 3D point Clouds Loic Landireu [
Slides
]
KPConv: Flexible and Deformable Convolution for Point Clouds [
,
git
]
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds [
,
git
]
Tools/SW/Packages
Python bindings for Point Cloud Library [
git
]
Open3D [
link
]
pyntcloud [
link
]
PyVista [
link
]
torch-points3d : Pytorch framework for doing deep learning on point clouds [
link
]
Geometric Deep Learning Extension Library for [PyTorch
link
]
kaolin : A PyTorch Library for Accelerating 3D Deep Learning Research [
link
]
PyTorch3D : FAIR‘s library of reusable components for deep learning with 3D data [
link
]
PCDet Toolbox in PyTorch for 3D Object Detection from Point Cloud [
link
]
pointcloudset: Efficient analysis of large datasets of point clouds recorded over time [
link
]