Papers
Topics
Authors
Recent
Search
2000 character limit reached

Geometry Depth Consistency in RGBD Relative Pose Estimation

Published 1 Jan 2024 in cs.CV | (2401.00639v1)

Abstract: Relative pose estimation for RGBD cameras is crucial in a number of applications. Previous approaches either rely on the RGB aspect of the images to estimate pose thus not fully making use of depth in the estimation process or estimate pose from the 3D cloud of points that each image produces, thus not making full use of RGB information. This paper shows that if one pair of correspondences is hypothesized from the RGB-based ranked-ordered correspondence list, then the space of remaining correspondences is restricted to corresponding pairs of curves nested around the hypothesized correspondence, implicitly capturing depth consistency. This simple Geometric Depth Constraint (GDC) significantly reduces potential matches. In effect this becomes a filter on possible correspondences that helps reduce the number of outliers and thus expedites RANSAC significantly. As such, the same budget of time allows for more RANSAC iterations and therefore additional robustness and a significant speedup. In addition, the paper proposed a Nested RANSAC approach that also speeds up the process, as shown through experiments on TUM, ICL-NUIM, and RGBD Scenes v2 datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. OpenSfM. https://github.com/mapillary/OpenSfM/tree/main.
  2. Relative pose solvers using monocular depth. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 4037–4043. IEEE, 2022.
  3. Direct RGB-D visual odometry based on hybrid strategy. IEEE Sensors Journal, 21(20):23278–23288, 2021.
  4. Benchmarking pedestrian odometry: The brown pedestrian odometry dataset (bpod). In 2022 International Conference on 3D Vision (3DV), pages 1–11. IEEE, 2022.
  5. Edge-direct visual odometry. arXiv preprint arXiv:1906.04838, 2019.
  6. Superpoint: Self-supervised interest point detection and description. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 224–236, 2018.
  7. Self-supervised correspondence estimation via multiview registration. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1216–1225, 2023.
  8. Trifocal relative pose from lines at points. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  9. Information-driven direct RGB-D odometry. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4929–4937, 2020.
  10. SID-SLAM: Semi-direct information-driven RGB-D SLAM. IEEE Robotics and Automation Letters, 2023.
  11. Unsupervised histological image registration using structural feature guided convolutional neural network. IEEE Transactions on Medical Imaging, 41(9):2414–2431, 2022.
  12. Continuous direct sparse visual odometry from RGB-D images. arXiv preprint arXiv:1904.02266, 2019.
  13. A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM. In 2014 IEEE international conference on Robotics and automation (ICRA), pages 1524–1531. IEEE, 2014.
  14. KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In Proceedings of the 24th annual ACM symposium on User interface software and technology, pages 559–568, 2011.
  15. Unsupervised feature learning for 3D scene labeling. In 2014 IEEE International Conference on Robotics and Automation (ICRA), pages 3050–3057, 2014.
  16. Adaptive continuous visual odometry from RGB-D images. arXiv preprint arXiv:1910.00713, 2019.
  17. A robust keyframe-based visual slam for RGB-D cameras in challenging scenarios. IEEE Access, 2023.
  18. Learnable motion coherence for correspondence pruning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3237–3246, 2021.
  19. David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60:91–110, 2004.
  20. Locality preserving matching. International Journal of Computer Vision, 127:512–531, 2019.
  21. OpenMVG: Open multiple view geometry. In Reproducible Research in Pattern Recognition: First International Workshop, RRPR 2016, Cancún, Mexico, December 4, 2016, Revised Selected Papers 1, pages 60–74. Springer, 2017.
  22. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE transactions on robotics, 33(5):1255–1262, 2017.
  23. Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4938–4947, 2020.
  24. Structure-from-motion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4104–4113, 2016.
  25. Structure PLP-SLAM: Efficient sparse mapping and localization using point, line and plane for monocular, RGB-D and stereo cameras. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 2105–2112. IEEE, 2023.
  26. Modeling the world from internet photo collections. International journal of computer vision, 80:189–210, 2008.
  27. A benchmark for the evaluation of RGB-D SLAM systems. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 573–580, 2012.
  28. Global-aware registration of less-overlap RGB-D scans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6357–6366, 2022.
  29. Loftr: Detector-free local feature matching with transformers. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8922–8931, 2021.
  30. Robust multiview point cloud registration with reliable pose graph initialization and history reweighting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9506–9515, 2023a.
  31. Guiding local feature matching with surface curvature. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 17981–17991, 2023b.
  32. Extreme relative pose estimation for RGB-D scans via scene completion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4531–4540, 2019.
  33. RGB-D DSO: Direct sparse odometry with RGB-D cameras for indoor scenes. IEEE Transactions on Multimedia, 24:4092–4101, 2021.
  34. Learning two-view correspondences and geometry using order-aware network. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5845–5854, 2019.
  35. Go-slam: Global optimization for consistent 3d instant reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3727–3737, 2023.
  36. A tutorial on quantitative trajectory evaluation for visual (-inertial) odometry. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 7244–7251. IEEE, 2018.
  37. Robust depth-aided RGBD-inertial odometry for indoor localization. Measurement, page 112487, 2023.
  38. Canny-VO: Visual odometry with RGB-D cameras based on geometric 3D-2D edge alignment. IEEE Transactions on Robotics, 35(1):184–199, 2018.
  39. Nice-slam: Neural implicit scalable encoding for slam. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12786–12796, 2022.

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