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].”
MethodAccuracy of typical photogrammetric networks in cultural heritage 3D modeling projects
Nocerino, E., Menna, F., & Fabio Remondino, A. (2014) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsarchives-xl-5-465-2014 · Cited by 103
“A similar problem was investigated in Cohen et al. (2012) where symmetries are exploited to constraint the bundle adjustment and avoid deformations in object space - although a simple strengthen of the imaging network would have been a much easier and practical solution.”
BackgroundDense Semantic 3D Reconstruction
Häne, C., Zach, C., Cohen, A., & Pollefeys, M. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2613051 · Cited by 93
“To align the voxel grid with the scene, we use the approach described in [7].”
MethodSelf-citationNetwork Principles for SfM: Disambiguating Repeated Structures with Local Context
Wilson, K., & Snavely, N. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.69 · Cited by 69
“[2] detect symmetries while reconstructing, exploiting them to improve reconstruction accuracy.”
3D DIGITIZATION OF MUSEUM CONTENT WITHIN THE 3DICONS PROJECT
Barsanti, S. G., & Guidi, G. (2013) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-5-w1-151-2013 · Cited by 60
Coupled structure-from-motion and 3D symmetry detection for urban facades
Ceylan, D., Mitra, N. J., Zheng, Y., & Pauly, M. V. (2014) · ACM Transactions on Graphics · doi:10.1145/2517348 · Cited by 67
“In a follow-up work, Cohen et al. [2012] propose to use symmetry priors with collinearity and orthogonality constraints in an additional bundle adjustment step to reduce drifts in a given initial SfM output.”
MethodInfluentialA Symmetry Prior for Convex Variational 3D Reconstruction
Speciale, P., Oswald, M. R., Cohen, A., & Pollefeys, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_19 · Cited by 69
“Cohen et al. [2] detect symmetries in sparse point clouds by using appearance-based 3D-3D point matching in a RANSAC-based procedure.”
MethodSelf-citationSavinov, N., Häne, C., Ladický, Ľ., & Pollefeys, M. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.589 · Cited by 62
“Those camera poses are either provided with the dataset (as in the Middlebury Benchmark [27] or in the Thin Road Sign dataset [32]) or computed via structure from motion algorithm [3] (as in the semantic reconstruction experiments).”
MethodSelf-citationDiscrete optimization of ray potentials for semantic 3D reconstruction
Savinov, N., Ladický, Ľ., Häne, C., & Pollefeys, M. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299190 · Cited by 58
“Experiments We tested our algorithm on6 datasets - South Building [11], Catania [11], CAB [5], Castle-P30 [24], Providence [11] and Vienna Opera [5].”
MethodSelf-citationIndoor-Outdoor 3D Reconstruction Alignment
Cohen, A., Schönberger, J. L., Speciale, P., Sattler, T., Frahm, J., & Pollefeys, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_18 · Cited by 46
“[6] actively detect and exploit symmetries and repetitions to improve the quality of SfM reconstructions.”
BackgroundMethodSelf-citationFlight Dynamics-Based Recovery of a UAV Trajectory Using Ground Cameras
Rozantsev, A., Sinha, S. N., Dey, D., & Fua, P. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.266 · Cited by 39
“Sometimes, regularization is incorporated into bundle adjustment via soft geometric constraints on the 3D structure, including planarity [34], 3D symmetry [35], bound constraints [36] and prior knowledge of 3D shape [37].”
BackgroundSelf-citationLine-sweep: Cross-ratio for wide-baseline matching and 3D reconstruction
Ramalingam, S., Antunes, M., Snow, D., Lee, G. H., & Pillai, S. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298728 · Cited by 35
“We gathered two data sets (109 images of a Quadrangle, 32 images in Oxford) and we used two other data sets CAB and Barcelona from [4].”
MethodCorrecting for Duplicate Scene Structure in Sparse 3D Reconstruction
Heinly, J., Dunn, E., & Frahm, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10593-2_51 · Cited by 34
“Duplicate structure has been of recent interest in the research community and has motivated a variety of applications [3,8,14,22,23,25,28].”
BackgroundMerging the Unmatchable: Stitching Visually Disconnected SfM Models
Cohen, A., Sattler, T., & Pollefeys, M. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.246 · Cited by 33
“, to challenges posed by repetitive structures [3,4,6,23], the fact that there might not always be enough images to obtain a single reconstruction remains a fundamental problem.”
BackgroundMethodInfluentialSelf-citationDistinguishing the Indistinguishable: Exploring Structural Ambiguities via Geodesic Context
Yan, Q., Yang, L., Zhang, L., & Xiao, C. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.24 · Cited by 33
“Such pattern provides an informative prior for applications, like image completion [15], monocular modeling [17, 25, 31], bundle readjustment [9] and scene stitching [8].”
MethodDetecting Approximate Reflection Symmetry in a Point Set Using Optimization on Manifold
Nagar, R., & Raman, S. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2893835 · Cited by 27
“detect symmetry using geometric and image cues [18].”
MethodA fast and efficient 3D reflection symmetry detector based on neural networks
Ji, P., & Liu, X. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08043-9 · Cited by 25
“[28] explored the reflection symmetry or repeating architecture to reduce the alignment Multimedia Tools and Applications (2019) 78:35 71–35 92 4 4 35473”
Background3DSymm: Robust and Accurate 3D Reflection Symmetry Detection
Nagar, R., & Raman, S. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107483 · Cited by 27
A Minimal Solution for Non-perspective Pose Estimation from Line Correspondences
Lee, G. H. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46454-1_11 · Cited by 22
“The depths that correspond to the end points of the 2D image lines are uniformly drawn from a range of [5, 10] m.”
BackgroundMethodMO-SLAM: Multi object SLAM with run-time object discovery through duplicates
Dharmasiri, T., Lui, V., & Drummond, T. W. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759203 · Cited by 20
“Jiang et al. proposed a similar approach in [11] where they search for missing correspondences in the whole scene by reprojecting 3D points into images instead of local regions.”
BackgroundGrasping surfaces of revolution: Simultaneous pose and shape recovery from two views
Phillips, C. J., Lecce, M., Davis, C., & Daniilidis, K. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139366 · Cited by 11
“Recent approaches addressing camera calibration and the reconstruction of 3D objects from one or multiple views exploited geometric properties such as repetitivity [3], [4] or symmetry [5], [6].”
BackgroundBinocular 3D Object Recovery Using a Symmetry Prior
Michaux, A., Kumar, V., Jayadevan, V., Delp, E. J., & Pizlo, Z. (2017) · Symmetry · doi:10.3390/sym9050064 · Cited by 10
“This approach was pursued to clean up the 3D point clouds generated from the application of structure from motion [42,43].”
MethodMultistage SFM: A Coarse-to-Fine Approach for 3D ReconstructionPreprint
Shah, R., Deshpande, A., & Narayanan, P. J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.06235 · Cited by 11
Bundle adjustment using aerial images with two-stage geometric verification
Kume, H., Sato, T., & Yokoya, N. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.05.003 · Cited by 10
“In an approach related to loop closing, Cohen et al. [25] exploited symmetries, which often exist in man-made structures, instead of loops.”
BackgroundQuick textured mesh generation in Cultural Heritage digitization
Guidi, G., Navarro, P. R., Barsanti, S. G., Micoli, L. L., & Russo, M. (2013) · IRIS Research product catalog (Sapienza University of Rome) · Cited by 10
Towards realistic symmetry-based completion of previously unseen point clouds
Rumezhak, T., Dobosevych, O., Hryniv, R. O., Selotkin, V., Karpiv, V., & Maksymenko, M. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00287 · Cited by 9
“[6] propose a method to recover symmetry relations using the geometry cues.”
The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network
Jiang, C., Yuan, Y., Lang, H., Ding, S., & Lu, J. (2022) · Journal of Advanced Transportation · doi:10.1155/2022/2238095 · Cited by 12
“3D technologies applied in pavement inspection include 3D structure light [30, 31], laser scanning [32], and binocular stereo vision [33]”
Quick textured mesh generation for massive 3D digitization of museum artifacts
Barsanti, S. G., Micoli, L. L., & Guidi, G. (2013) · Digital Heritage International Congress · doi:10.1109/digitalheritage.2013.6743732 · Cited by 9
Wang, X., Xiao, T., Gruber, M. A., & Heipke, C. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00349 · Cited by 9
“) [3], Indoor (Ind.”
MethodRobust extrinsic symmetry estimation in 3D point clouds
Nagar, R. (2024) · The Visual Computer · doi:10.1007/s00371-024-03313-6 · Cited by 8
Recovering Correct Reconstructions from Indistinguishable Geometry
Heinly, J., Dunn, E., & Frahm, J. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.84 · Cited by 7
“[11] locate planes of symmetry within a scene, and then use these as constraints in bundle adjustment.”
BackgroundScalable non-rigid registration for multi-view stereo data
Palma, G., Boubekeur, T., Ganovelli, F., & Cignoni, P. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.06.012 · Cited by 7
“[11] propose a new SfM formulation to solve”
BackgroundGlobally Optimal Point Set Registration by Joint Symmetry Plane Fitting
Hu, L., & Kneip, L. (2021) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-021-01024-4 · Cited by 9
“[10] detect symmetries in sparse point clouds by using appearance-based 3D-3D point correspondences in a RANSAC scheme.”
BackgroundMethodInfluentialTowards Better 3D Model Accuracy with Spherical Photogrammetry
Pramulyo, H., Harto, A. B., Mertotaroeno, S. H., & Murtiyoso, A. (2016) · Lecture notes in geoinformation and cartography · doi:10.1007/978-3-319-45123-7_8 · Cited by 7
Wang, X., & Heipke, C. (2020) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.86.5.299 · Cited by 6
Architectural decomposition for 3D landmark building understanding
Kobyshev, N., Riemenschneider, H., Bódis-Szomorú, A., & Gool, L. V. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477653 · Cited by 6
Progressive Structure from Motion by Iteratively Prioritizing and Refining Match Pairs
Xiao, T., Yan, Q., Ma, W., & Deng, F. (2021) · Remote Sensing · doi:10.3390/rs13122340 · Cited by 5
“Table 2 lists the image datasets used in our experiments, consisting of five small public datasets (Books, Cereal, Cup, Desk and Street [8]), three middle-scale datasets Indoor, Templeof-Heaven (ToH) [8], and Redmond [41]), three benchmark datasets (B1, B2, B3 [26]), and one large image set (Church [29]).”
MethodInfluentialSymmetry based 3D reconstruction of repeated cylinders
Miglani, A., Roy, S. D., Chaudhury, S., & Srivastava, J. B. (2013) · National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) · doi:10.1109/ncvpripg.2013.6776266 · Cited by 5
“It is widely used for image segmentation and retrieving three dimensional structure and pose and computing structure from motion [2][3][4][5].”
MethodLeveraging Camera Triplets for Efficient and Accurate Structure-from-Motion
Manam, L., & Govindu, V. M. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00474 · Cited by 4
“Cohen et al. [4] detected symmetries by estimating similarity transforms and removing false edges to reduce drift.”
BackgroundAn overview of recent progress in volumetric semantic 3D reconstruction
Häne, C., & Pollefeys, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900143 · Cited by 5
Self-citationEstimating the Number of Correct Matches Using Only Spatial Order
Talker, L., Moses, Y., & Shimshoni, I. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2869560 · Cited by 4
“Each method was tested on the following three datasets: “LunchRoom” [58], “Barcelona” [59] and “PersonHall” [60], which consist of 72, 191 and 330 images, respectively.”
MethodInfluentialThe Palmieri hypogeum in Lecce from the integrated survey to the dissemination of contents
Gabellone, F., Ferrari, I., Giuri, F., & Chiffi, M. (2015) · 2015 Digital Heritage · doi:10.1109/digitalheritage.2015.7413878 · Cited by 4
Efficient architectural structural element decomposition
Kobyshev, N., Riemenschneider, H., Bódis-Szomorú, A., & Gool, L. V. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.06.004 · Cited by 3
“Cohen et al. Cohen et al. (2012) take it one step further and let the symmetries influence the Structure-from-Motion optimization, whereas Kser et al. (2011) exploit mirror symmetries in dense re-constructions from a single view.”
BackgroundUsing Spatial Order to Boost the Elimination of Incorrect Feature Matches
Talker, L., Moses, Y., & Shimshoni, I. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.200 · Cited by 3
“We use the dataset “Barcelona” [8], which consists of 191 images taken from all around a building.”
MethodRevealing Hidden 3-D Reflection Symmetry
Nagar, R., & Raman, S. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2620380 · Cited by 3
“The proposed method differs from [31] in two significant”
Method6DOF decoupled roto-translation alignment of large-scale indoor point clouds
Al-Nuaimi, A., Hilsenbeck, S., Garcea, A., & Steinbach, E. G. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.08.004 · Cited by 3
A hybrid CRF framework for semantic 3D reconstruction
Ma, Z., Shen, X., & Cao, C. (2017) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/3139131.3139170 · Cited by 2
“In order to prove the efficiency of our proposed framework, we use four datasets, including Castle-P30[Strecha et al. 2008] , museum [Ladicky et al. 2012] , CAB [Pollefeys 2012] and barcelona [Polle-feys 2012], to finish our experiments.”
MethodMultiscale TILT Feature Detection with Application to Geometric Image Segmentation
Lam, C.-P., Yang, A. Y., Elhamifar, E., & Sastry, S. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.79 · Cited by 2
“In urban-scene modeling, symmetric texture regions are also widely used [32, 15, 5].”
BackgroundAn Image Dataset of Bishnupur Terracotta Temples for Digital Heritage Research
Ghorai, M., Santra, S., Samanta, S., Purkait, P., & Chanda, B. (2018) · Springer eBooks · doi:10.1007/978-981-10-7221-5_13 · Cited by 2
Discrete Optimization of Ray Potentials for Semantic 3D ReconstructionPreprint
Savinov, N., Ladický, Ľ., Häne, C., & Pollefeys, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.10491 · Cited by 2
“Experiments We tested our algorithm on6 datasets - South Building [11], Catania [11], CAB [5], Castle-P30 [24], Providence [11] and Vienna Opera [5].”
MethodSelf-citationSipiran, I. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223488 · Cited by 1
Enhanced Back-Projection of Vision Features for 3D Symmetry Detection
Aguirre, I., & Sipiran, I. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00015 · Cited by 1
“…organizing principle for 3D shape analysis, leveraged for compression, structure inference, and downstream understanding across CAD, computer vision, medicine, archaeology, and graphics modeling [4, 7, 9, 11, 13, 19, 20, 24, 31–35, 38, 42, 44, 47, 48, 58, 63, 64, 66–68, 74–76, 79, 82].”
Approximate reflection symmetry in a point set: theory and algorithm with an application
Nagar, R., & Raman, S. (2017) · Cited by 1
The Combination of Spherical Photogrammetry and UAV for 3D Modeling
Ihsanudin, T., & Affriani, A. R. (2017) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/98/1/012057 · Cited by 1
“3D modelling with IBM used to reconstructs the geometry object by identifying the same set of points from two or more photographs [2].”
MethodRecovering the 3D Geometry of Heritage Monuments from Image Collections
Shah, R., Deshpande, A., Namboodiri, A., & Narayanan, P. J. (2017) · Springer eBooks · doi:10.1007/978-981-10-5738-0_8 · Cited by 1
An Image-Based Approach for 3D Reconstruction of Urban Scenes Using Architectural Symmetries
Srinivasan, N., & Dellaert, F. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00049 · Cited by 1
“In comparison to earlier work in this vein [3, 25, 1, 24, 8] we increase the types of symmetries that can be used, ranging from primitive symmetries [18] to complex symmetry groups.”
BackgroundInfluentialRobustly Modeling The World From Photos
Wilson, K. L. (2016) · ProQuest Demo Repository · doi:10.7298/x40p0wx1
“[15] detect symmetries while reconstructing, exploiting them to improve reconstruction accuracy.”
Robust Estimation of Reflection Symmetry in Noisy and Partial 3D Point Clouds.Preprint
Nagar, R. (2021) · arXiv (Cornell University)
Multi-view Urban Scene Reconstruction with Continuous Adjustment
Ma, Z., Hong, D., Sui, X., & Shen, X. (2021) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc52933.2021.9563392
Bertamini, M., & Griffin, L. D. (2017) · MDPI eBooks · doi:10.3390/books978-3-03842-497-0 · Cited by 1
LVG-SfM: Learning-Based View-Graph Generation for Robust on-the-Fly SfM
Gan, W., Yu, Y., Perda, G., Morelli, L., Xia, R., Zhan, Z., Wang, X., & Fabio Remondino, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91569-7_11
“[41] analyze missing correspondences among various overlapping images to check the correctness of the corresponding image pairs, [5] exploit ambiguous matches to first recover symmetry and then impose it as an additional constraint in bundle adjustment, [11] proposes a post-processing solution,…”
Unifying Viewgraph Sparsification and Disambiguation of Repeated Structures in Structure-from-Motion
Manam, L., & Govindu, V. M. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02681-3
Coarse-to-fine outlier correction with applications in structure from motion
Du, S., Liu, Y., Huang, Z., Wu, P., & Li, J. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.07.008
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.