LiDAR 3D Object Detection

Published: 09 Oct 2015 Category: deep_learning

Papers

Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Complex-YOLO: Real-time 3D Object Detection on Point Clouds

Focal Loss in 3D Object Detection

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

3D Object Detection Using Scale Invariant and Feature Reweighting Networks

3D Backbone Network for 3D Object Detection

https://arxiv.org/abs/1901.08373

Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds

https://arxiv.org/abs/1904.07537

Point-Voxel CNN for Efficient 3D Deep Learning

IoU Loss for 2D/3D Object Detection

Deep Hough Voting for 3D Object Detection in Point Clouds

Fast Point R-CNN

Interpolated Convolutional Networks for 3D Point Cloud Understanding

PointPillars: Fast Encoders for Object Detection from Point Clouds

LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

  • intro: CVPR 2019
  • intro: winner of nuScenes 3D Object Detection challenge in WAD
  • arxiv: https://arxiv.org/abs/1908.09492
  • github: https://github.com/ZhengWG/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection

End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds

SampleNet: Differentiable Point Cloud Sampling

TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges

Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

https://arxiv.org/abs/2208.13414

3DSSD: Point-based 3D Single Stage Object Detector

HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection

SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review

Structure Aware Single-stage 3D Object Detection from Point Cloud

Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection

SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds

https://arxiv.org/abs/2006.04043

Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection

https://arxiv.org/abs/2006.05187

Generative Sparse Detection Networks for 3D Single-shot Object Detection

Local Grid Rendering Networks for 3D Object Detection in Point Clouds

https://arxiv.org/abs/2007.02099

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

Pillar-based Object Detection for Autonomous Driving

Weakly Supervised 3D Object Detection from Lidar Point Cloud

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Part-Aware Data Augmentation for 3D Object Detection in Point Cloud

https://arxiv.org/abs/2007.13373

Weakly Supervised 3D Object Detection from Point Clouds

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Global Context Aware Convolutions for 3D Point Cloud Understanding

https://arxiv.org/abs/2008.02986

DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDAR

PointMixup: Augmentation for Point Clouds

Cross-Modality 3D Object Detection

LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks

https://arxiv.org/abs/2008.10309

Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving

DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution

Joint Pose and Shape Estimation of Vehicles from LiDAR Data

Deep Learning for 3D Point Cloud Understanding: A Survey

Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection

Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds

MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving

StrObe: Streaming Object Detection from LiDAR Packets

MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models

LiDAR-based Panoptic Segmentation via Dynamic Shifting Network

CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device

https://arxiv.org/abs/2012.13801

Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving

Self-Attention Based Context-Aware 3D Object Detection

A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection

Stereo CenterNet based 3D Object Detection for Autonomous Driving

https://arxiv.org/abs/2103.11071

LiDAR R-CNN: An Efficient and Universal 3D Object Detector

HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection

Group-Free 3D Object Detection via Transformers

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

BEVDetNet: Bird’s Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Driving

https://arxiv.org/abs/2104.10780

Investigating Attention Mechanism in 3D Point Cloud Object Detection

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

  • intro: ICCV 2021
  • intro: The Chinese University of Hong Kong & Huawei Noah’s Ark Lab & HKUST & Sun Yat-Sen University
  • arxiv: https://arxiv.org/abs/2109.02499

Voxel Transformer for 3D Object Detection

  • intro: ICCV 2021
  • intro: The Chinese University of Hong Kong & National University of Singapore & Huawei Noah’s Ark Lab & HKUST & Sun Yat-Sen University
  • arxiv: https://arxiv.org/abs/2109.02497

A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation

Point Density-Aware Voxels for LiDAR 3D Object Detection

VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

Point2Seq: Detecting 3D Objects as Sequences

OccAM’s Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images

Voxel Field Fusion for 3D Object Detection

Unifying Voxel-based Representation with Transformer for 3D Object Detection

LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network

  • intro: TuSimple & University of Central Florida
  • intro: Official 1st Place Solution for the Waymo Open Dataset Challenges 2022 - 3D Semantic Segmentation
  • arxiv: https://arxiv.org/abs/2206.11428

Rethinking IoU-based Optimization for Single-stage 3D Object Detection

Embracing Single Stride 3D Object Detector with Sparse Transformer

Fully Sparse 3D Object Detection

Anchor-free 3D Detection

Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

  • intro: Samsung Inc & Johns Hopkins University & South China University of Technology
  • keywords: Object as Hotspots (OHS)
  • arxiv: https://arxiv.org/abs/1912.12791

CenterNet3D: An Anchor free Object Detector for Autonomous Driving

AFDet: Anchor Free One Stage 3D Object Detection

  • intro: Horizon Robotics
  • intro: CVPR Workshop 2020
  • intro: Baseline detector for the 1st place solutions of Waymo Open Dataset Challenges 2020
  • arxiv: https://arxiv.org/abs/2006.12671

Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness

1st Place Solution for Waymo Open Dataset Challenge – 3D Detection and Domain Adaptation

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

3D Semantic Segmentation

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

Cloud Transformers

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

Projected-point-based Segmentation: A New Paradigm for LiDAR Point Cloud Segmentation

https://arxiv.org/abs/2008.03928

pseudo-LiDAR

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection

Rethinking Pseudo-LiDAR Representation

Demystifying Pseudo-LiDAR for Monocular 3D Object Detection

Is Pseudo-Lidar needed for Monocular 3D Object detection?

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection

Multi-Modal 3D Object Detection

  • intro: University of Science and Technology & Harbin Institute of Technology & SenseTime Research & The Chinese University of Hong Kong & IIIS, Tsinghua University AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
  • arxiv: https://arxiv.org/abs/2201.06493

3D Detection and Tracking

Joint Monocular 3D Vehicle Detection and Tracking

Center-based 3D Object Detection and Tracking

3D Object Detection and Tracking Based on Streaming Data

Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss

Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving

PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds

Real-time 3D Single Object Tracking with Transformer

3D MOT

AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

Monocular Quasi-Dense 3D Object Tracking

https://arxiv.org/abs/2103.07351

Lite-FPN for Keypoint-based Monocular 3D Object Detection

RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection

VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars

https://arxiv.org/abs/2107.02980

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving

CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion

  • intro: Based on this work, we achieved 1st place on the nuScenes tracking leaderboard
  • intro: Tsinghua University & Mogo Auto
  • arxiv: https://arxiv.org/abs/2209.02540

Transformer

Point Transformer

Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving

https://arxiv.org/abs/2011.13628

Point Transformer

3D Object Detection with Pointformer

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

Improving 3D Object Detection with Channel-wise Transformer

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

Projects

OpenLidarPerceptron

Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds

Resources

Awesome-Automanous-3D-Detection-Methods

https://github.com/tyjiang1997/awesome-Automanous-3D-detection-methods