Discovering and exploiting 3D symmetries in structure from motion
The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Many architectural scenes contain symmetric or repeated structures, which can generate erroneous image correspondences during structure from motion (Sfm) computation. Prior work has shown that the detection and removal of these incorrect matches is crucial for accurate and robust recovery of scene structure. In this paper, we point out that these incorrect matches, in fact, provide strong cues to the existence of symmetries and structural regularities in the unknown 3D structure. We make two key contributions. First, we propose a method to recover various symmetry relations in the structure using geometric and appearance cues. A set of structural constraints derived from the symmetries are imposed within a new constrained bundle adjustment formulation, where symmetry priors are also incorporated. Second, we show that the recovered symmetries enable us to choose a natural coordinate system for the 3D structure where gauge freedom in rotation is held fixed. Furthermore, based on the symmetries, 3D structure completion is also performed. Our approach significantly reduces drift through ”structural” loop closures and improves the accuracy of reconstructions in urban scenes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Bundle Adjustment — A Modern Synthesis
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44480-7_21 · Cited by 3,988
Multiple View Geometry in Computer Vision
(2001) · Kybernetes · doi:10.1108/k.2001.30.9_10.1333.2 · Cited by 3,336
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
Cummins, M., & Newman, P. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364908090961 · Cited by 1,472
Generalizing motion edits with Gaussian processes
Ikemoto, L., Arikan, O., & Forsyth, D. (2009) · ACM Transactions on Graphics · doi:10.1145/1477926.1477927 · Cited by 1,214
Square Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing
Dellaert, F., & Kaess, M. (2006) · The International Journal of Robotics Research · doi:10.1177/0278364906072768 · Cited by 922
SBA: A software package for generic sparse bundle adjustment
Lourakis, M. I. A., & Argyros, A. A. (2009) · ACM Transactions on Mathematical Software · doi:10.1145/1486525.1486527 · Cited by 788
Detailed Real-Time Urban 3D Reconstruction from Video
Pollefeys, M., Nistér, D., Frahm, J.-M., Akbarzadeh, A., Mordohai, P., Clipp, B., Engels, C., Gallup, D., Kim, S.-J., Merrell, P., et al. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0086-4 · Cited by 717
Self-citationPartial and approximate symmetry detection for 3D geometry
Mitra, N. J., Guibas, L. J., & Pauly, M. (2006) · ACM Transactions on Graphics · doi:10.1145/1141911.1141924 · Cited by 529
Research works printed but not linked: 1
- engels, 2006, Bundle adjustment rules, Photogrammetric Computer Vision
Cited by
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
“Recent efforts in this direction include [18], [52], [231].”
Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
A survey of structure from motion.
Özyeşil, O., Voroninski, V., Basri, R., & Singer, A. (2017) · Acta Numerica · doi:10.1017/s096249291700006x · Cited by 489
“utational eciency of their disambiguation technique. For alternative approaches aiming to resolve the diculties in SfM for symmetric and ambiguous scenes, we refer the reader to other sources, e.g. [14, 66, 60, 45, 55]. 6.3 Alternative Features and Camera Models Our discussion in the previous sections has mainly focus…”
MethodInfluentialJoint 3D Scene Reconstruction and Class Segmentation
Hane, C., Zach, C., Cohen, A., Angst, R., & Pollefeys, M. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.20 · Cited by 213
“To align the voxel grid with the scene we use the approach described in [5].”
MethodSelf-citationA Review of Three-Dimensional Imaging Technologies for Pavement Distress Detection and Measurements
Mathavan, S., Kamal, K., & Rahman, M. (2015) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2015.2428655 · Cited by 192
“By using multiple 2D images obtained from the same camera, point correspondences are established leading to the 3D depth reconstruction of the scene [37].”
Method
Metadata
- Authors
- Cohen, A., Zach, C., Sinha, S. N., & Pollefeys, M.
- Affiliations
- ETH Zurich (CH)
- Microsoft Research (United Kingdom) (GB)
- Microsoft (United States) (US)
- Venue
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 1514-1521
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2044914660
- Cited by
- 67
- References
- 39
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 2 · 2022: 1 · 2021: 5 · 2020: 2 · 2019: 4 · 2018: 4 · 2017: 9 · 2016: 16 · 2015: 9 · 2014: 4 · 2013: 7
- FWCI
- 4.54
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Keywords
- structure from motion, structural constraints, coordinate system selection, gauge freedom, loop closure, urban scene reconstruction, architectural scenes
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.