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

iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds (2312.15449v1)

Published 24 Dec 2023 in cs.CV

Abstract: Accurately annotating multiple 3D objects in LiDAR scenes is laborious and challenging. While a few previous studies have attempted to leverage semi-automatic methods for cost-effective bounding box annotation, such methods have limitations in efficiently handling numerous multi-class objects. To effectively accelerate 3D annotation pipelines, we propose iDet3D, an efficient interactive 3D object detector. Supporting a user-friendly 2D interface, which can ease the cognitive burden of exploring 3D space to provide click interactions, iDet3D enables users to annotate the entire objects in each scene with minimal interactions. Taking the sparse nature of 3D point clouds into account, we design a negative click simulation (NCS) to improve accuracy by reducing false-positive predictions. In addition, iDet3D incorporates two click propagation techniques to take full advantage of user interactions: (1) dense click guidance (DCG) for keeping user-provided information throughout the network and (2) spatial click propagation (SCP) for detecting other instances of the same class based on the user-specified objects. Through our extensive experiments, we present that our method can construct precise annotations in a few clicks, which shows the practicality as an efficient annotation tool for 3D object detection.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Point cloud geometry prediction across spatial scale using deep learning. In 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), 70–73. IEEE.
  2. Interactive object counting. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III 13, 504–518. Springer.
  3. nuScenes: A multimodal dataset for autonomous driving. IEEE Transactions on Intelligent Transportation Systems.
  4. Sasa: Semantics-augmented set abstraction for point-based 3d object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 221–229.
  5. Rethinking click embedding for deep interactive image segmentation. IEEE Transactions on Industrial Informatics, 19(1): 261–273.
  6. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11): 1231–1237.
  7. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, 3354–3361. IEEE.
  8. Deep learning for 3d point clouds: A survey. IEEE transactions on pattern analysis and machine intelligence, 43(12): 4338–4364.
  9. Edgeflow: Achieving practical interactive segmentation with edge-guided flow. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1551–1560.
  10. Structure aware single-stage 3d object detection from point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11873–11882.
  11. Learning semantic segmentation of large-scale point clouds with random sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11): 8338–8354.
  12. LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXVII, 248–265. Springer.
  13. Interactive image segmentation via backpropagating refinement scheme. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5297–5306.
  14. Interactive Object Segmentation in 3D Point Clouds. arXiv preprint arXiv:2204.07183.
  15. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 12697–12705.
  16. Interactive Multi-Class Tiny-Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14136–14145.
  17. Sustech points: A portable 3d point cloud interactive annotation platform system. In 2020 IEEE Intelligent Vehicles Symposium (IV), 1108–1115. IEEE.
  18. 3D IoU-Net: IoU guided 3D object detector for point clouds. arXiv preprint arXiv:2004.04962.
  19. Interactive image segmentation with latent diversity. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 577–585.
  20. Interactive image segmentation with first click attention. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 13339–13348.
  21. SS3D: Sparsely-Supervised 3D Object Detection from Point Cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8428–8437.
  22. Tanet: Robust 3d object detection from point clouds with triple attention. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 11677–11684.
  23. Exploring Active 3D Object Detection from a Generalization Perspective. In The Eleventh International Conference on Learning Representations.
  24. 3D object detection for autonomous driving: a review and new outlooks. arXiv preprint arXiv:2206.09474.
  25. Deep hough voting for 3d object detection in point clouds. In proceedings of the IEEE/CVF International Conference on Computer Vision, 9277–9286.
  26. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 652–660.
  27. Learning to count everything. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 3394–3403.
  28. Interactive annotation of 3D object geometry using 2D scribbles. In European Conference on Computer Vision, 751–767. Springer.
  29. Pointrcnn: 3d object proposal generation and detection from point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 770–779.
  30. From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE transactions on pattern analysis and machine intelligence, 43(8): 2647–2664.
  31. Point-gnn: Graph neural network for 3d object detection in a point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1711–1719.
  32. f-brs: Rethinking backpropagating refinement for interactive segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8623–8632.
  33. Reviving iterative training with mask guidance for interactive segmentation. In 2022 IEEE International Conference on Image Processing (ICIP), 3141–3145. IEEE.
  34. LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Tracking. arXiv preprint arXiv:1904.09085.
  35. Voting for voting in online point cloud object detection. In Robotics: science and systems, volume 1, 10–15. Rome, Italy.
  36. Pillar-based object detection for autonomous driving. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXII 16, 18–34. Springer.
  37. Redal: Region-based and diversity-aware active learning for point cloud semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 15510–15519.
  38. Rpvnet: A deep and efficient range-point-voxel fusion network for lidar point cloud segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16024–16033.
  39. Deep interactive object selection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 373–381.
  40. Second: Sparsely embedded convolutional detection. Sensors, 18(10): 3337.
  41. 3dssd: Point-based 3d single stage object detector. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11040–11048.
  42. A late fusion cnn for digital matting. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 7469–7478.
  43. Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 18953–18962.
  44. Cia-ssd: Confident iou-aware single-stage object detector from point cloud. In Proceedings of the AAAI conference on artificial intelligence, volume 35, 3555–3562.
  45. Voxelnet: End-to-end learning for point cloud based 3d object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4490–4499.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Dongmin Choi (4 papers)
  2. Wonwoo Cho (5 papers)
  3. Kangyeol Kim (9 papers)
  4. Jaegul Choo (161 papers)
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