Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection (2308.03982v2)

Published 8 Aug 2023 in cs.CV

Abstract: Recently, polar-based representation has shown promising properties in perceptual tasks. In addition to Cartesian-based approaches, which separate point clouds unevenly, representing point clouds as polar grids has been recognized as an alternative due to (1) its advantage in robust performance under different resolutions and (2) its superiority in streaming-based approaches. However, state-of-the-art polar-based detection methods inevitably suffer from the feature distortion problem because of the non-uniform division of polar representation, resulting in a non-negligible performance gap compared to Cartesian-based approaches. To tackle this issue, we present PARTNER, a novel 3D object detector in the polar coordinate. PARTNER alleviates the dilemma of feature distortion with global representation re-alignment and facilitates the regression by introducing instance-level geometric information into the detection head. Extensive experiments show overwhelming advantages in streaming-based detection and different resolutions. Furthermore, our method outperforms the previous polar-based works with remarkable margins of 3.68% and 9.15% on Waymo and ONCE validation set, thus achieving competitive results over the state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. nuscenes: A multimodal dataset for autonomous driving. In CVPR, 2020.
  2. To the point: Efficient 3d object detection in the range image with graph convolution kernels. In CVPR, 2021.
  3. Polarstream: Streaming object detection and segmentation with polar pillars. Advances in Neural Information Processing Systems, 2021.
  4. Shuai Li Chenhang He, Ruihuang Li and Lei Zhang. Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In CVPR, 2022.
  5. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint, 2020.
  6. Embracing single stride 3d object detector with sparse transformer. In CVPR, 2022.
  7. Rangedet: In defense of range view for lidar-based 3d object detection. In ICCV, 2021.
  8. Strobe: Streaming object detection from lidar packets. In CoRL, 2021.
  9. Deep ordinal regression network for monocular depth estimation. In CVPR, 2018.
  10. Streaming object detection for 3-d point clouds. In ECCV, 2020.
  11. Axial attention in multidimensional transformers. arXiv preprint, 2019.
  12. Pointpillars: Fast encoders for object detection from point clouds. In CVPR, 2019.
  13. Rangercnn: Towards fast and accurate 3d object detection with range image representation. arXiv preprint, 2020.
  14. Focal loss for dense object detection. In ICCV, 2017.
  15. Ssd: Single shot multibox detector. In Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling, editors, ECCV, 2016.
  16. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, 2021.
  17. Pyramid r-cnn: Towards better performance and adaptability for 3d object detection. In ICCV, 2021.
  18. One million scenes for autonomous driving: Once dataset. arXiv preprint, 2021.
  19. Voxel transformer for 3d object detection. In ICCV, 2021.
  20. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR, 2017.
  21. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 2017.
  22. Categorical depth distribution network for monocular 3d object detection. In CVPR, 2021.
  23. Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In CVPR, 2020.
  24. Pointrcnn: 3d object proposal generation and detection from point cloud. In CVPR, 2019.
  25. Scalability in perception for autonomous driving: Waymo open dataset. In CVPR, 2020.
  26. Swformer: Sparse window transformer for 3d object detection in point clouds. In ECCV, 2022.
  27. Pillar-based object detection for autonomous driving. In ECCV, 2020.
  28. Point2seq: Detecting 3d objects as sequences. In CVPR, 2022.
  29. Second: Sparsely embedded convolutional detection. Sensors, 2018.
  30. 3dssd: Point-based 3d single stage object detector. In CVPR, 2020.
  31. Std: Sparse-to-dense 3d object detector for point cloud. In ICCV, 2019.
  32. Center-based 3d object detection and tracking. arXiv preprint, 2020.
  33. Polarnet: An improved grid representation for online lidar point clouds semantic segmentation. In CVPR, 2020.
  34. Understanding the robustness in vision transformers. In ICML, 2022.
  35. End-to-end multi-view fusion for 3d object detection in lidar point clouds. In CoRL, 2020.
  36. Voxelnet: End-to-end learning for point cloud based 3d object detection. In CVPR, 2018.
  37. Centerformer: Center-based transformer for 3d object detection. In ECCV, 2022.
  38. Conquer: Query contrast voxel-detr for 3d object detection. In CVPR, 2023.
  39. Cylindrical and asymmetrical 3d convolution networks for lidar segmentation. In CVPR, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (10)
  1. Ming Nie (5 papers)
  2. Yujing Xue (5 papers)
  3. Chunwei Wang (13 papers)
  4. Chaoqiang Ye (8 papers)
  5. Hang Xu (205 papers)
  6. Xinge Zhu (62 papers)
  7. Qingqiu Huang (17 papers)
  8. Michael Bi Mi (21 papers)
  9. Xinchao Wang (203 papers)
  10. Li Zhang (693 papers)
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now