Papers
Topics
Authors
Recent
Search
2000 character limit reached

Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scene

Published 30 Jan 2023 in cs.CV | (2301.12972v3)

Abstract: This paper proposes EyeNet, a novel semantic segmentation network for point clouds that addresses the critical yet often overlooked parameter of coverage area size. Inspired by human peripheral vision, EyeNet overcomes the limitations of conventional networks by introducing a simple but efficient multi-contour input and a parallel processing network with connection blocks between parallel streams. The proposed approach effectively addresses the challenges of dense point clouds, as demonstrated by our ablation studies and state-of-the-art performance on Large-Scale Outdoor datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Sensaturban evaluation server. https://github.com/QingyongHu/SensatUrban. Accessed: 2022-11-11.
  2. Semantickitti: A dataset for semantic scene understanding of lidar sequences. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9297–9307, 2019.
  3. The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4413–4421, 2018.
  4. Multi-feature aggregation for semantic segmentation of an urban scene point cloud. Remote Sensing, 14(20):5134, 2022.
  5. Emergent properties of foveated perceptual systems. arXiv preprint arXiv:2006.07991, 2020.
  6. Scf-net: Learning spatial contextual features for large-scale point cloud segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14504–14513, 2021.
  7. Sideeye: A generative neural network based simulator of human peripheral vision. arXiv preprint arXiv:1706.04568, 2017.
  8. Sum: A benchmark dataset of semantic urban meshes. ISPRS Journal of Photogrammetry and Remote Sensing, 179:108–120, 2021.
  9. Omni-supervised point cloud segmentation via gradual receptive field component reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11673–11682, 2021.
  10. Peripheral-foveal vision for real-time object recognition and tracking in video. 2007.
  11. 3d semantic segmentation with submanifold sparse convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9224–9232, 2018.
  12. Semantic3d. net: A new large-scale point cloud classification benchmark. arXiv preprint arXiv:1704.03847, 2017.
  13. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7132–7141, 2018.
  14. Towards semantic segmentation of urban-scale 3d point clouds: A dataset, benchmarks and challenges. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4977–4987, 2021.
  15. Randla-net: Efficient semantic segmentation of large-scale point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11108–11117, 2020.
  16. Epnet: Enhancing point features with image semantics for 3d object detection. CoRR, abs/2007.08856, 2020.
  17. Large-scale point cloud semantic segmentation with superpoint graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4558–4567, 2018.
  18. Tgnet: Geometric graph cnn on 3-d point cloud segmentation. IEEE Transactions on Geoscience and Remote Sensing, 58(5):3588–3600, 2019.
  19. Fg-net: Fast large-scale lidar point clouds understanding network leveraging correlated feature mining and geometric-aware modelling. arXiv preprint arXiv:2012.09439, 2020.
  20. Multi-scale point-wise convolutional neural networks for 3d object segmentation from lidar point clouds in large-scale environments. IEEE Transactions on Intelligent Transportation Systems, 22(2):821–836, 2019.
  21. Peripheral vision transformer. arXiv preprint arXiv:2206.06801, 2022.
  22. Semantic segmentation with peripheral vision. In Advances in Visual Computing: 15th International Symposium, ISVC 2020, San Diego, CA, USA, October 5–7, 2020, Proceedings, Part II 15, pages 421–429. Springer, 2020.
  23. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
  24. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017.
  25. Semantic segmentation of large-scale outdoor point clouds by encoder–decoder shared mlps with multiple losses. Remote Sensing, 13(16):3121, 2021.
  26. The isprs benchmark on urban object classification and 3d building reconstruction. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences I-3 (2012), Nr. 1, 1(1):293–298, 2012.
  27. Paris-rue-madame database: a 3d mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods. In 4th international conference on pattern recognition, applications and methods ICPRAM 2014, 2014.
  28. Toronto-3d: A large-scale mobile lidar dataset for semantic segmentation of urban roadways. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 202–203, 2020.
  29. Tangent convolutions for dense prediction in 3d. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3887–3896, 2018.
  30. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6411–6420, 2019.
  31. Terramobilita/iqmulus urban point cloud analysis benchmark. Computers & Graphics, 49:126–133, 2015.
  32. Dales: A large-scale aerial lidar data set for semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 186–187, 2020.
  33. Graph attention convolution for point cloud semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10296–10305, 2019.
  34. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5):1–12, 2019.
  35. Continuous mapping convolution for large-scale point clouds semantic segmentation. IEEE Geoscience and Remote Sensing Letters, 19:1–5, 2021.
  36. 3d-cvf: Generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection. CoRR, abs/2004.12636, 2020.
  37. Point transformer, 2020.
Citations (8)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up