Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DCDet: Dynamic Cross-based 3D Object Detector (2401.07240v2)

Published 14 Jan 2024 in cs.CV

Abstract: Recently, significant progress has been made in the research of 3D object detection. However, most prior studies have focused on the utilization of center-based or anchor-based label assignment schemes. Alternative label assignment strategies remain unexplored in 3D object detection. We find that the center-based label assignment often fails to generate sufficient positive samples for training, while the anchor-based label assignment tends to encounter an imbalanced issue when handling objects of varying scales. To solve these issues, we introduce a dynamic cross label assignment (DCLA) scheme, which dynamically assigns positive samples for each object from a cross-shaped region, thus providing sufficient and balanced positive samples for training. Furthermore, to address the challenge of accurately regressing objects with varying scales, we put forth a rotation-weighted Intersection over Union (RWIoU) metric to replace the widely used L1 metric in regression loss. Extensive experiments demonstrate the generality and effectiveness of our DCLA and RWIoU-based regression loss. The Code will be available at https://github.com/Say2L/DCDet.git.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Voxel r-cnn: Towards high performance voxel-based 3d object detection. In AAAI, 2021.
  2. Embracing single stride 3d object detector with sparse transformer. In CVPR, 2022.
  3. Fully sparse 3d object detection. In NeurIPS, 2022.
  4. Afdet: Anchor free one stage 3d object detection. arXiv preprint arXiv:2006.12671, 2020.
  5. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430, 2021.
  6. Are we ready for autonomous driving? the kitti vision benchmark suite. In CVPR, 2012.
  7. Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In CVPR, 2022.
  8. Afdetv2: Rethinking the necessity of the second stage for object detection from point clouds. In AAAI, 2022.
  9. Pointpillars: Fast encoders for object detection from point clouds. In CVPR, 2019.
  10. Lidar r-cnn: An efficient and universal 3d object detector. In CVPR, 2021.
  11. Pillarnext: Rethinking network designs for 3d object detection in lidar point clouds. In CVPR, 2023.
  12. Focal loss for dense object detection. In ICCV, 2017.
  13. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR, 2017.
  14. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In NeurIPS, 2017.
  15. Generalized intersection over union: A metric and a loss for bounding box regression. In CVPR, 2019.
  16. Rethinking iou-based optimization for single-stage 3d object detection. In ECCV, 2022.
  17. Pointrcnn: 3d object proposal generation and detection from point cloud. In CVPR, 2019.
  18. Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In CVPR, 2020.
  19. From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. TPAMI, 2020.
  20. Pillarnet: Real-time and high-performance pillar-based 3d object detection. In ECCV, 2022.
  21. Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection. IJCV, 2023.
  22. Scalability in perception for autonomous driving: Waymo open dataset. In CVPR, 2020.
  23. Swformer: Sparse window transformer for 3d object detection in point clouds. In ECCV, 2022.
  24. OpenPCDet Development Team. Openpcdet: An open-source toolbox for 3d object detection from point clouds. https://github.com/open-mmlab/OpenPCDet, 2020.
  25. Fcos: Fully convolutional one-stage object detection. In ICCV, 2019.
  26. 3d-centernet: 3d object detection network for point clouds with center estimation priority. Pattern Recognition, 2021.
  27. Dsvt: Dynamic sparse voxel transformer with rotated sets. In CVPR, 2023.
  28. Behind the curtain: Learning occluded shapes for 3d object detection. In AAAI, 2022.
  29. Second: Sparsely embedded convolutional detection. Sensors, 2018.
  30. 3dssd: Point-based 3d single stage object detector. In CVPR, 2020.
  31. Center-based 3d object detection and tracking. In CVPR, 2021.
  32. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In CVPR, 2020.
  33. Focal and efficient iou loss for accurate bounding box regression. Neurocomputing, 2022.
  34. Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. In CVPR, 2022.
  35. Distance-iou loss: Faster and better learning for bounding box regression. In AAAI, 2020.
  36. Cia-ssd: Confident iou-aware single-stage object detector from point cloud. In AAAI, 2021.
  37. Voxelnet: End-to-end learning for point cloud based 3d object detection. In CVPR, 2018.
  38. Iou loss for 2d/3d object detection. In 3DV, 2019.
  39. Objects as points. arXiv preprint arXiv:1904.07850, 2019.
  40. Centerformer: Center-based transformer for 3d object detection. In ECCV, 2022.
  41. Autoassign: Differentiable label assignment for dense object detection. arXiv preprint arXiv:2007.03496, 2020.
Citations (1)
View on Semantic Scholar

Summary

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

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

GitHub

  1. GitHub - Say2L/DCDet: Implementation of "DCDet: Dynamic Cross-based 3D Object Detector" (10 stars)