Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection

3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity in training sample allocation based on box Intersection over Union (IoU_box). This problem impedes further enhancements in the performance of anchor-based LiDAR 3D object detectors. To tackle this challenge, this paper introduces a new training sample selection method that utilizes point cloud distribution for anchor sample quality measurement, named Point Assisted Sample Selection (PASS). This method has undergone rigorous evaluation on two widely utilized datasets. Experimental results demonstrate that the application of PASS elevates the average precision of anchor-based LiDAR 3D object detectors to a novel state-of-the-art, thereby proving the effectiveness of the proposed approach. The codes will be made available at https://github.com/XJTU-Haolin/Point_Assisted_Sample_Selection.

[1]  Jie Ma,et al.  RS-Aug: Improve 3D Object Detection on LiDAR With Realistic Simulator Based Data Augmentation , 2023, IEEE Transactions on Intelligent Transportation Systems.

[2]  Inyong Koo,et al.  PG-RCNN: Semantic Surface Point Generation for 3D Object Detection , 2023, 2023 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Liang Zhao,et al.  Deep Dive into Gradients: Better Optimization for 3D Object Detection with Gradient-Corrected IoU Supervision , 2023, Computer Vision and Pattern Recognition.

[4]  Xiaodong Yang,et al.  PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Shuchang Zhou,et al.  UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jiaxin Chen,et al.  OcTr: Octree-Based Transformer for 3D Object Detection , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Jiaya Jia,et al.  VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Tengyu Ma,et al.  LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross- Modal Fusion , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Shaoshuai Shi,et al.  Virtual Sparse Convolution for Multimodal 3D Object Detection , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Wanli Ouyang,et al.  GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Hai Wu,et al.  Transformation-Equivariant 3D Object Detection for Autonomous Driving , 2022, AAAI.

[12]  Dongfang Yang,et al.  3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestration , 2022, ArXiv.

[13]  Xiaofei He,et al.  Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph , 2022, ECCV.

[14]  Gim Hee Lee,et al.  Rethinking IoU-based Optimization for Single-stage 3D Object Detection , 2022, ECCV.

[15]  Hongsheng Li,et al.  3D Object Detection for Autonomous Driving: A Comprehensive Survey , 2022, International Journal of Computer Vision.

[16]  Geonwoo Baek,et al.  itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Ruifeng Li,et al.  PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection , 2022, ECCV.

[18]  Ming-Yu Liu,et al.  3D Object Detection with a Self-supervised Lidar Scene Flow Backbone , 2022, ECCV.

[19]  Jiaya Jia,et al.  Focal Sparse Convolutional Networks for 3D Object Detection , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Yulan Guo,et al.  Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Lei Zhang,et al.  Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Xiaopei Wu,et al.  Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Steven L. Waslander,et al.  Point Density-Aware Voxels for LiDAR 3D Object Detection , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Justin Solomon,et al.  Object DGCNN: 3D Object Detection using Dynamic Graphs , 2021, NeurIPS.

[25]  Rohit Girdhar,et al.  An End-to-End Transformer Model for 3D Object Detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[26]  Minzhe Niu,et al.  Voxel Transformer for 3D Object Detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[27]  Minzhe Niu,et al.  Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Edward Johns,et al.  AGO-Net: Association-Guided 3D Point Cloud Object Detection Network , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Yang Wang,et al.  PVGNet: A Bottom-Up One-Stage 3D Object Detector with Integrated Multi-Level Features , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Bumsub Ham,et al.  HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Zhichao Li,et al.  LiDAR R-CNN: An Efficient and Universal 3D Object Detector , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Zhaoxiang Zhang,et al.  RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[33]  Jianping Shi,et al.  PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection , 2021, International Journal of Computer Vision.

[34]  Wengang Zhou,et al.  Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection , 2020, AAAI.

[35]  Li Jiang,et al.  CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud , 2020, AAAI.

[36]  Yue Wang,et al.  Pillar-based Object Detection for Autonomous Driving , 2020, ECCV.

[37]  Larry S. Davis,et al.  InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling , 2020, ECCV.

[38]  Jian Sun,et al.  AutoAssign: Differentiable Label Assignment for Dense Object Detection , 2020, ArXiv.

[39]  Philipp Krähenbühl,et al.  Center-based 3D Object Detection and Tracking , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  B. Zeng,et al.  SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds , 2020, AAAI.

[41]  Liang Du,et al.  Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Lei Zhang,et al.  Structure Aware Single-Stage 3D Object Detection From Point Cloud , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Xinge Zhu,et al.  SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds , 2020, ECCV.

[44]  Shuangjie Xu,et al.  HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Yanan Sun,et al.  3DSSD: Point-Based 3D Single Stage Object Detector , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Xiaogang Wang,et al.  PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  A. Yuille,et al.  Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots , 2019, ECCV.

[48]  Xin Zhao,et al.  TANet: Robust 3D Object Detection from Point Clouds with Triple Attention , 2019, AAAI.

[49]  R. Socher,et al.  Learning From Noisy Anchors for One-Stage Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  D. Ramanan,et al.  What You See is What You Get: Exploiting Visibility for 3D Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Dragomir Anguelov,et al.  Scalability in Perception for Autonomous Driving: Waymo Open Dataset , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Shifeng Zhang,et al.  Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  Alex H. Lang,et al.  PointPainting: Sequential Fusion for 3D Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[54]  Xiaoyong Shen,et al.  STD: Sparse-to-Dense 3D Object Detector for Point Cloud , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[55]  Xiaogang Wang,et al.  From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[56]  Qiang Xu,et al.  nuScenes: A Multimodal Dataset for Autonomous Driving , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Carlos Vallespi-Gonzalez,et al.  LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[58]  Jiong Yang,et al.  PointPillars: Fast Encoders for Object Detection From Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[59]  Xiaogang Wang,et al.  PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[60]  Bo Li,et al.  SECOND: Sparsely Embedded Convolutional Detection , 2018, Sensors.

[61]  Bin Yang,et al.  PIXOR: Real-time 3D Object Detection from Point Clouds , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[62]  Yin Zhou,et al.  VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[63]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[64]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[65]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.