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

Linear Relative Pose Estimation Founded on Pose-only Imaging Geometry (2401.13357v1)

Published 24 Jan 2024 in cs.CV

Abstract: How to efficiently and accurately handle image matching outliers is a critical issue in two-view relative estimation. The prevailing RANSAC method necessitates that the minimal point pairs be inliers. This paper introduces a linear relative pose estimation algorithm for n $( n \geq 6$) point pairs, which is founded on the recent pose-only imaging geometry to filter out outliers by proper reweighting. The proposed algorithm is able to handle planar degenerate scenes, and enhance robustness and accuracy in the presence of a substantial ratio of outliers. Specifically, we embed the linear global translation (LiGT) constraint into the strategies of iteratively reweighted least-squares (IRLS) and RANSAC so as to realize robust outlier removal. Simulations and real tests of the Strecha dataset show that the proposed algorithm achieves relative rotation accuracy improvement of 2 $\sim$ 10 times in face of as large as 80% outliers.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Speeded-up robust features (SURF). Computer vision and image understanding, 110(3):346–359, 2008.
  2. Visual reconstruction. MIT press, 1987.
  3. Equivalent constraints for two-view geometry: Pose solution/pure rotation identification and 3d reconstruction. International Journal of Computer Vision, 127:163–180, 2019.
  4. A pose-only solution to visual reconstruction and navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):73–86, 2021.
  5. Robust relative rotation averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4):958–972, 2017.
  6. Fast and accurate image matching with cascade hashing for 3d reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1–8, 2014.
  7. A review on robust M-estimators for regression analysis. Computers & Chemical Engineering, 147:107254, 2021.
  8. Dealing with degeneracy in essential matrix estimation. In IEEE International Conference on Image Processing, pages 1964–1967, 2008.
  9. Olivier Faugeras. Three-dimensional computer vision: a geometric viewpoint. MIT press, 1993.
  10. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981.
  11. Multiple view geometry in computer vision. Cambridge university press, 2003.
  12. Robust regression using iteratively reweighted least-squares. Communications in Statistics-theory and Methods, 6(9):813–827, 1977.
  13. Peter J Huber. Robust estimation of a location parameter. In Breakthroughs in statistics: Methodology and distribution, pages 492–518. Springer, 1992.
  14. Peter J Huber. Robust statistics. John Wiley & Sons, 2004.
  15. Image feature information extraction for interest point detection: A comprehensive review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4694–4712, 2023.
  16. OpenGV: A unified and generalized approach to real-time calibrated geometric vision. In 2014 IEEE International Conference on Robotics and Automation (ICRA), pages 1–8. IEEE, 2014.
  17. Direct optimization of frame-to-frame rotation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2352–2359, 2013.
  18. Finding the exact rotation between two images independently of the translation. In European Conference on Computer Vision, pages 696–709, 2012.
  19. H Christopher Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature, 293(5828):133–135, 1981.
  20. David G Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60:91–110, 2004.
  21. Adaptive structure from motion with a contrario model estimation. In Asian Conference on Computer Vision, pages 257–270. Springer, 2013.
  22. Openmvg: Open multiple view geometry. In Reproducible Research in Pattern Recognition, pages 60–74, 2017.
  23. David Nistér. An efficient solution to the five-point relative pose problem. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6):756–770, 2004.
  24. A survey of structure from motion. Acta Numerica, 26:305–364, 2017.
  25. On the convergence of irls and its variants in outlier-robust estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 17808–17818, 2023.
  26. Johan Philip. A non-iterative algorithm for determining all essential matrices corresponding to five point pairs. The Photogrammetric Record, 15(88):589–599, 1996.
  27. J. Philip. Critical point configurations of the 5-, 6-, 7-, and 8-point algorithms for relative orientation. Technical Report TRITA-MAT-1998-MA-13, KTH Royal Institute of Technology, 1998.
  28. Relative pose estimation for instrumented, calibrated imaging platforms. In DICTA, pages 601–612, 2003.
  29. Peter J Rousseeuw. Least median of squares regression. Journal of the American Statistical Association, 79(388):871–880, 1984.
  30. ORB: An efficient alternative to SIFT or SURF. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2564–2571, 2011.
  31. Structure-from-motion revisited. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4104–4113, 2016.
  32. Recent developments on direct relative orientation. ISPRS Journal of Photogrammetry and Remote Sensing, 60(4):284–294, 2006.
  33. Richard Szeliski. Computer vision: algorithms and applications. Springer Nature, 2022.
  34. Ji Zhao. An efficient solution to non-minimal case essential matrix estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4):1777–1792, 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Qi Cai (40 papers)
  2. Xinrui Li (24 papers)
  3. Yuanxin Wu (36 papers)

Summary

  • The paper introduces a novel LiRP algorithm that processes batches of point pairs using pose-only imaging geometry for accurate relative pose estimation.
  • The paper leverages a linear global translation constraint integrated with IRLS and RANSAC to effectively manage high outlier ratios and planar degenerate scenes.
  • The paper demonstrates robust performance on the Strecha dataset, achieving rotation errors below one degree even under significant noise, enhancing SLAM and SfM applications.

Introduction

In the exploration of efficient and robust two-view relative pose estimation, one of the foremost computational challenges faced pertains to the handling of outliers in image matching. Traditional robust estimation methods like RANSAC have certain limitations, such as the requirement for a majority of minimal point pairs to be inliers. Addressing these challenges, a new linear relative pose estimation algorithm has been developed, utilizing recent advances in pose-only imaging geometry. This innovative approach facilitates the processing of a batch of point pairs simultaneously (with n≥6), thereby enhancing accuracy while handling planar degenerate scenes and substantial outlier ratios effectively.

Algorithm Overview

At the core of this algorithm lies the integration of the linear global translation (LiGT) constraint into iterative reweighted least squares (IRLS) and RANSAC methods, which leads to a significant improvement in the robustness of outlier removal. The algorithm, dubbed LiRP (Linear Relative Pose), differs from classical approaches by using pose-only imaging geometry to identify outliers instead of relying on point correspondences to solve the essential matrix. This decouples the 3D scene from camera pose and allows the algorithm to solve for global translations linearly, thus it can handle specific degenerate motions, which classical methods struggle with.

Experimental Validation

Through extensive simulation and empirical tests, including those on the Strecha dataset, the LiRP algorithm demonstrated its capacity to maintain high accuracy in relative rotation estimation – even with an 80% presence of outliers. It showed a noticeable improvement over established methods like the Stewenius five-point algorithm and others supported by OpenGV, especially in handling planar scenes. Importantly, noise tests confirmed the robustness of LiRP, showcasing its competency in maintaining rotation error lower than one degree amid increasing noise.

Conclusion and Further Work

The proposed LiRP algorithm represents a significant stride forward in relative pose estimation under the challenge of outlier management. Its ability to provide a robust, accurate framework for such scenarios is underpinned by well-structured simulation and real-world results. Notably, this work illuminates a path for further research on refinement strategies that could potentially eliminate the need for parameter tuning inherent in methods like IRLS and RANSAC, further propelling advancements in 3D visual computing applications like SLAM and SfM.

File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown