Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating (2404.05187v1)

Published 8 Apr 2024 in cs.CV, cs.GR, and cs.RO

Abstract: Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying. However, existing algorithms usually rely on conflicting raw observations as training data, resulting in poor map performance. In this paper, we propose LGSDF, an ESDF continual Global learning algorithm aided by Local updating. At the front end, axis-aligned grids are dynamically updated by pre-processed sensor observations, where incremental fusion alleviates estimation error caused by limited viewing directions. At the back end, a randomly initialized implicit ESDF neural network performs continual self-supervised learning guided by these grids to generate smooth and continuous maps. The results on multiple scenes show that LGSDF can construct more accurate ESDF maps and meshes compared with SOTA (State Of The Art) explicit and implicit mapping algorithms. The source code of LGSDF is publicly available at https://github.com/BIT-DYN/LGSDF.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. K. Eisenträger, J. Haubner, J. Brade, et al., “Evaluating the effects of virtual reality environment learning on subsequent robot teleoperation in an unfamiliar building,” IEEE Transactions on Visualization and Computer Graphics, vol. 29, no. 5, pp. 2220–2229, 2023.
  2. J. Leng, L. Wang, X. Liu, et al., “Efficient flower text entry in virtual reality,” IEEE Transactions on Visualization and Computer Graphics, vol. 28, no. 11, pp. 3662–3672, 2022.
  3. X. Li, R. Li, G. Chen, et al., “A rotation-invariant framework for deep point cloud analysis,” IEEE transactions on visualization and computer graphics, vol. 28, no. 12, pp. 4503–4514, 2021.
  4. Y. Deng, M. Wang, Y. Yang, et al., “See-csom: Sharp-edged and efficient continuous semantic occupancy mapping for mobile robots,” IEEE Transactions on Industrial Electronics, 2023.
  5. J. J. Park, P. Florence, J. Straub, et al., “Deepsdf: Learning continuous signed distance functions for shape representation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 165–174, 2019.
  6. Z. Zhu, S. Peng, V. Larsson, et al., “Nice-slam: Neural implicit scalable encoding for slam,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12 786–12 796, 2022.
  7. G.-W. Yang, W.-Y. Zhou, H.-Y. Peng, et al., “Recursive-nerf: An efficient and dynamically growing nerf,” IEEE Transactions on Visualization and Computer Graphics, 2022.
  8. B. Mildenhall, P. P. Srinivasan, M. Tancik, et al., “Nerf: Representing scenes as neural radiance fields for view synthesis,” Communications of the ACM, vol. 65, no. 1, pp. 99–106, 2021.
  9. L. Mescheder, M. Oechsle, M. Niemeyer, et al., “Occupancy networks: Learning 3d reconstruction in function space,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4460–4470, 2019.
  10. H. Li, X. Yang, H. Zhai, et al., “Vox-surf: Voxel-based implicit surface representation,” IEEE Transactions on Visualization and Computer Graphics, 2022.
  11. H. Oleynikova, Z. Taylor, M. Fehr, et al., “Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning,” in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1366–1373.   IEEE, 2017.
  12. J. Ortiz, A. Clegg, J. Dong, et al., “isdf: Real-time neural signed distance fields for robot perception,” in 2022 Robotics: Science and Systems (RSS).   IEEE, 2022.
  13. M. Rostami, S. Kolouri, and P. K. Pilly, “Complementary learning for overcoming catastrophic forgetting using experience replay,” arXiv preprint arXiv:1903.04566, 2019.
  14. Y. Deng, M. Wang, Y. Yang, et al., “Hd-ccsom: Hierarchical and dense collaborative continuous semantic occupancy mapping through label diffusion,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2417–2422.   IEEE, 2022.
  15. A. Hornung, K. M. Wurm, M. Bennewitz, et al., “Octomap: An efficient probabilistic 3d mapping framework based on octrees,” Autonomous robots, vol. 34, no. 3, pp. 189–206, 2013.
  16. D. Meyer-Delius, M. Beinhofer, and W. Burgard, “Occupancy grid models for robot mapping in changing environments,” in Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012.
  17. Y. Deng, M. Wang, D. Wang, et al., “S-mki: Incremental dense semantic occupancy reconstruction through multi-entropy kernel inference,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3824–3829.   IEEE, 2022.
  18. B. Curless and M. Levoy, “A volumetric method for building complex models from range images,” in Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, pp. 303–312, 1996.
  19. R. A. Newcombe, S. Izadi, O. Hilliges, et al., “Kinectfusion: Real-time dense surface mapping and tracking,” in 2011 10th IEEE international symposium on mixed and augmented reality, pp. 127–136.   Ieee, 2011.
  20. A. Dai, M. Nießner, M. Zollhöfer, et al., “Bundlefusion: Real-time globally consistent 3d reconstruction using on-the-fly surface reintegration,” ACM Transactions on Graphics (ToG), vol. 36, no. 4, p. 1, 2017.
  21. L. Han, F. Gao, B. Zhou, et al., “Fiesta: Fast incremental euclidean distance fields for online motion planning of aerial robots,” in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4423–4430.   IEEE, 2019.
  22. D. Zhu, C. Wang, W. Wang, et al., “Vdb-edt: An efficient euclidean distance transform algorithm based on vdb data structure,” arXiv preprint arXiv:2105.04419, 2021.
  23. S. Weder, J. Schonberger, M. Pollefeys, et al., “Routedfusion: Learning real-time depth map fusion,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4887–4897, 2020.
  24. J. Huang, S.-S. Huang, H. Song, et al., “Di-fusion: Online implicit 3d reconstruction with deep priors,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8932–8941, 2021.
  25. J. Wang, T. Bleja, and L. Agapito, “Go-surf: Neural feature grid optimization for fast, high-fidelity rgb-d surface reconstruction,” in 2022 International Conference on 3D Vision (3DV), pp. 433–442.   IEEE, 2022.
  26. X. Zhong, Y. Pan, J. Behley, et al., “Shine-mapping: Large-scale 3d mapping using sparse hierarchical implicit neural representations,” in 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 8371–8377.   IEEE, 2023.
  27. E. Sucar, S. Liu, J. Ortiz, et al., “imap: Implicit mapping and positioning in real-time,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6229–6238, 2021.
  28. Z. Yan, Y. Tian, X. Shi, et al., “Continual neural mapping: Learning an implicit scene representation from sequential observations,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15 782–15 792, 2021.
  29. J. T. Barron, B. Mildenhall, D. Verbin, et al., “Mip-nerf 360: Unbounded anti-aliased neural radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470–5479, 2022.
  30. W. E. Lorensen and H. E. Cline, “Marching cubes: A high resolution 3d surface construction algorithm,” ACM siggraph computer graphics, vol. 21, no. 4, pp. 163–169, 1987.
  31. A. Szot, A. Clegg, E. Undersander, et al., “Habitat 2.0: Training home assistants to rearrange their habitat,” Advances in Neural Information Processing Systems, vol. 34, pp. 251–266, 2021.
  32. A. Dai, A. X. Chang, M. Savva, et al., “Scannet: Richly-annotated 3d reconstructions of indoor scenes,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5828–5839, 2017.
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