【分类/下载/代码/笔记】
版本 | 更新时间 | 更新内容 | 作者 | |
---|---|---|---|---|
1 | V 1.0 | 2021.12 | 论文分类整理 | W.P. Xiao |
2 | V 1.0.1 | 2022.1.7 | 更新code链接 | Y.Q. Wu |
目录
文章目录
3D Object Detection经典论文整理【分类/下载/代码/笔记】
笔者分类整理了与三维目标检测有关的经典论文和部分最新论文的PDF下载链接、开源代码、阅读笔记(部分)。笔者认为的必读经典论文通过加粗标识。论文主要按照Point-based和Voxel-based来划分,还包括一些交叉领域新的方向,比如Transformer、Self-ensembling等。[paper]
表示论文的下载链接,[code]
表示开源代码(包括Tensorflow代码tf-code
、PyTorch代码torch-code
),[note]
表示论文阅读笔记(小结)。更为完整的3D object detection paper list后续会在github上持续更新。
Point-based
-
PointNet系列
- CVPR 2017
[PointNet]
Deep Learning on Point Sets for 3D Classification and Segmentation [paper] [tf-code,torch-code] [note] - NIPS 2017
[PointNet++]
Deep Hierarchical Feature Learning on Point Sets in a Metric Space [paper] [tf-code,torch-code] [note] - CVPR 2018
[Frustum PointNets]
Frustum PointNets for 3D Object Detection from RGB-D Data [paper] [tf-code]
- CVPR 2017
-
CVPR 2019
[PointRCNN]
3D Object Proposal Generation and Detection From Point Cloud [paper] [torch-code] [note] -
ICCV 2019
[STD]
Sparse to Dense 3D Object Detector for Point Cloud [paper] [note] -
CVPR 2020 (Oral)
[3DSSD]
Point-based 3D Single Stage Object Detector [paper] -
VoteNet系列
Voxel-based
Anchor-based
- CVPR 2018
[VoxelNet]
End-to-End Learning for Point Cloud Based 3D Object Detection [paper] [tf-code] - Sensors 2018
[SECOND]
Sparsely Embedded Convolutional Detection [torch-code,torch-code] - CVPR 2019
[PointPillars]
Fast Encoders for Object Detection from Point Clouds [paper] [torch-code,torch-code] - CVPR 2020 (Oral)
[What You See is What You Get]
Exploiting Visibility for 3D Object Detection [paper] - PAMI 2020
[From Points to Parts]
3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network [paper] [torch-code] [note] - CVPR 2020
[SA-SSD]
Structure Aware Single-stage 3D Object Detection from Point Cloud - PV-RCNN系列
- CVPR 2020
[PV-RCNN]
Point-Voxel Feature Set Abstraction for 3D Object Detection [paper] [torch-code] [note] - ECCV 2020
[Deformable PV-RCNN]
Improving 3D Object Detection with Learned Deformations - arXiv 2021
[PV-RCNN++]
Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection [paper] [torch-code]
- CVPR 2020
- ECCV 2020
[SSN]
Shape Signature Networks for Multi-class Object Detection from Point Clouds [paper] [code] - AAAI 2021
[Voxel R-CNN]
Towards High Performance Voxel-based 3D Object Detection [paper] [torch-code] - AAAI 2021
[CIA-SSD]
Confident IoU-Aware Single-Stage Object Detector From Point Cloud [paper] [torch-code]
Anchor free
- ECCV 2020
[POD]
Pillar-based Object Detection for Autonomous Driving [paper] - ECCV 2020
[Object as Hotspots]
An Anchor-Free 3D Object Detection Approach via Firing of Hotspots [paper] - CVPR 2021
[Centerpoint]
Center-based 3D Object Detection and Tracking [paper] [torch-code]
Transformer/Self-attention/Attention
- AAAI 2020 (Oral)
[TANet]
Robust 3D Object Detection from Point Clouds with Triple Attention. [paper] [code] - CVPR 2020
[3DVID/PMPNet]
LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention. [paper] - arXiv 2021
[SA-Det3D]
Self-Attention Based Context-Aware 3D Object Detection [paper] [torch-code] - ICCV 2021
[CT3D]
Improving 3D Object Detection with Channel-wise Transformer [paper] [torch-code] - ICCV 2021
[VoTr]
Voxel Transformer for 3D Object Detection [paper] [torch-code] - ICCV 2021
[Pyramid R-CNN]
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection [paper] [torch-code] - arXiv 2021
[M3DeTR]
M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers [paper] [torch-code] - arXiv 2021
[SST]
Embracing Single Stride 3D Object Detector with Sparse Transformer [paper] [torch-code]
Multi-sensor
- CVPR 2018
[Frustum PointNets]
Frustum PointNets for 3D Object Detection from RGB-D Data [paper] [tf-code] - CVPR 2019
[UberATG-MMF]
Multi-Task Multi-Sensor Fusion for 3D Object Detection [paper] - IROS 2020
[CLOCs]
Camera-LiDAR Object Candidates Fusion for 3D Object Detection [paper] - CVPR 2020
[PointPainting]
Sequential Fusion for 3D Object Detection [paper] - arXiv 2021
[VPFNet]
Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion [paper]
Self-ensembling
- CVPR 2021
[SE-SSD]
Self-Ensembling Single-Stage Object Detector From Point Cloud [paper]
Unsupervised domain adaptation
- CVPR 2021
[ST3D]
Self-training for Unsupervised Domain Adaptation on 3D ObjectDetection - ICCV 2021
[SPG]
Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation [paper]