The DOI matches its Crossref record; 63 of the 64 references it cites were found in a registry or an index.
Efficient reconstruction of nonrigid shape and motion from real-time 3D scanner data
Abstract
We present a new technique for reconstructing a single shape and its nonrigid motion from 3D scanning data. Our algorithm takes a set of time-varying unstructured sample points that capture partial views of a deforming object as input and reconstructs a single shape and a deformation field that fit the data. This representation yields dense correspondences for the whole sequence, as well as a completed 3D shape in every frame. In addition, the algorithm automatically removes spatial and temporal noise artifacts and outliers from the raw input data. Unlike previous methods, the algorithm does not require any shape template but computes a fitting shape automatically from the input data. Our reconstruction framework is based upon a novel topology-aware adaptive subspace deformation technique that allows handling long sequences with complex geometry efficiently. The algorithm accesses data in multiple sequential passes, so that long sequences can be streamed from hard disk, not being limited by main memory. We apply the technique to several benchmark datasets, significantly increasing the complexity of the data that can be handled efficiently in comparison to previous work.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“[6] that can register 4D surfaces and produce an urshape template”
From Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013) · cites this paper as [6]
In the citing paper
“To alleviate it, [2], [6], [32] reduce the DoF explicitly by computing local transformations with respect to clusters or nodes, and most non-rigid registration methods use regularization to further constrain the solutions.”
From Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013) · cites this paper as [6]
In the citing paper
“[6], [28], [79] constructs a template, an urshape, by accumulating and filling in missing data from other scans in the same sequence.They have been used extensively in non-rigid registration to constrain dense correspondences [23], [29], [32], [34], [80].This works for objects with well defined forms, such as the human face and body.”
From Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013) · cites this paper as [6]
In the citing paper
“Yet, given only two surfaces and a high-dimensional deformation model (like [6], [32]), the solution can only be regularized by other prior knowledge-mostly in the form of regularizations to ensure smoothness.”
From Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013) · cites this paper as [6]
Citations
Cites
A Method for Registration of 3-D Shapes
Besl, P., & Mckay, N. D. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.121791 · Cited by 22,163
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(2017) · doi:10.1109/cvpr35066.2017 · Cited by 7,284
An Introduction to the Conjugate Gradient Method Without the Agonizing Pain
Shewchuk, J. R. (1994) · Cited by 2,193
2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
(2001) · 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.2001.990916 · Cited by 1,884
Terzopoulos, D., Platt, J. C., Barr, A. H., & Fleischer, K. (1987) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/37401.37427 · Cited by 1,716
SCAPE: shape completion and animation of people
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., & Davis, J. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073207 · Cited by 1,489
High-quality video view interpolation using a layered representation
Zitnick, C. L., Kang, S. B., Uyttendaele, M., Winder, S. A. J., & Szeliski, R. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015766 · Cited by 1,386
Nonlinear Programming: Analysis and Methods
Avriel, M. (1976) · CERN Document Server (European Organization for Nuclear Research) · Cited by 1,339
Nonlinear Programming Analysis and Methods
Rodin, E. Y. (1977) · Computers & Mathematics with Applications · doi:10.1016/0898-1221(77)90071-2 · Cited by 1,300
The space of human body shapes: reconstruction and parameterization from range scans
Allen, B., Curless, B., & Popović, Z. (2003) · ACM SIGGRAPH 2003 Papers · doi:10.1145/1201775.882311 · Cited by 913
Cited by
Sorted by citations
Items 101–136 of 136
Nonrigid Matching of Undersampled Shapes via Medial Diffusion
Berger, M., & Silva, C. T. (2012) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2012.03164.x · Cited by 4
“Other approaches [WAO ∗ 09, SAL ∗ 08] rely on point-to-plane distance correspondences, which implicitly assumes that the motion between frames is small.”
MethodXu, W., Du, W., Han, X., Li, Y., Ye, R., Wang, Y., & Lu, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00012 · Cited by 4
“The study of reconstructing general non-rigid objects with large deformation has a long history [48].”
Toward a real-time tracking of dense point-sampled geometry
Destelle, F., Céline Roudet, A., Neveu, M., & Dipandà, A. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6466875 · Cited by 4
An efficient volumetric method for non-rigid registration
Zhang, R., Chen, X., Shiratori, T., Tong, X., & Liu, L. (2015) · Graphical Models · doi:10.1016/j.gmod.2015.01.003 · Cited by 4
“Another method uses a subspace deformation model for registration of non-rigid shapes with fixed topology [11].”
MethodLeach, E., Cowley, E. E., & Bowen, C. J. (2024) · Journal of Foot and Ankle Research · doi:10.1002/jfa2.12047 · Cited by 3
“In the past decade, there has been a move towards sending the 3D scan files or cast/foam impressions alongside the patient's prescription to the manufacturer where adjustments are made based on geometry and clinician specifications [14, 15].”
BackgroundEfficient feature tracking of time-varying surfaces using multi-scale motion flow propagation
Liao, B., Xiao, C., & Pang, Z. (2013) · Computer-Aided Design · doi:10.1016/j.cad.2013.06.015 · Cited by 3
“[6] estimated a globally consistent template matching model for the reconstruction of deforming geometry from unstructured noisy point cloud sequences, they later improved their method in [25].”
3D Building Synthesis Based on Images and Affine Invariant Salient Features
Cohen, F. S., & Li, C. (2018) · Mediterranean Conference on Pattern Recognition and Artificial Intelligence (MedPRAI) · doi:10.1145/3177148.3180081 · Cited by 3
A two-stage approach to align two surfaces of deformable objects
Cao, V.-T., Tran, T.-T., & Laurendeau, D. (2015) · Graphical Models · doi:10.1016/j.gmod.2015.09.002 · Cited by 3
Funatomi, T., Takuya, Y., Ouchida, H., Iiyama, M., & Minoh, M. (2013) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2013.21 · Cited by 3
“Meanwhile, the motion parameters are derived from the configuration of the finger segments, which are acquired from the process of building a segment-wise shape model from a sequence of range data [3, 5, 12, 16].”
MethodPinhole-to-Projection Pyramid Subtraction for Reconstructing Non-rigid Objects from Range Images
Funatomi, T., Akuzawa, H., Iiyama, M., & Minoh, M. (2012) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2012.50 · Cited by 2
“Although other works [4, 7, 13] automatically estimated the object’s deformation without a template shape model, they did introduce a complex energy function that was optimized in an iterative manner.”
BackgroundMethodAnatomical Landmarks Localization for 3D Foot Point Clouds
Fung, S., Lu, X., Mykolaitis, M., Razzak, I., Kostkevičius, G., & Ozerenskis, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30111-7_53 · Cited by 2
Automated Capture of Real-time 3D Facial Geometry and Motion
Chi, J., & Zhang, C. (2011) · Computer-Aided Design and Applications · doi:10.3722/cadaps.2011.859-871 · Cited by 2
“[12] computes a fitting shape automatically from the real-time point clouds, but the computation is complex and time-consuming.”
BackgroundMirror Surface Assessment in Solar Power Applications by 2-D Coded Light
Li, S., Xu, J., Lou, J., Yang, X. C., Liu, H., & Chen, S. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2937529 · Cited by 2
“Thus, 3-D-scanner based mirror surface position measurement is seldom used [16], which aims at giving relative positions of sample points to a fixed global reference point.”
BackgroundParametric animation of performance‐captured mesh sequences
Casas, D., Tejera, M., Guillemaut, J., & Hilton, A. (2012) · Computer Animation and Virtual Worlds · doi:10.1002/cav.1430 · Cited by 1
Dynamic Human Surface Reconstruction Using a Single Kinect
Zeng, M., Zheng, J., Cheng, X., Jiang, B., & Liu, X. (2013) · International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics) · doi:10.1109/cadgraphics.2013.32 · Cited by 1
“[17] and Tevs et al.”
Neural Radiance Fields for Dynamic View Synthesis Using Local Temporal Priors
Chen, R., Zhao, J., Zhang, F., Chalmers, A., & Rhee, T. J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2095-8_5 · Cited by 1
“Non-rigid reconstruction [6, 16, 30, 40, 41, 50, 51] from monocular video (image sequence) is a challenging research problem for view synthesis.”
BackgroundRepairing topological inconsistency of mesh sequences
Feng, W., Zhang, H., Huang, J., Wang, C., & Bao, H. (2010) · Computer Animation and Virtual Worlds · doi:10.1002/cav.351 · Cited by 1
Latent Space Representation for Shape Analysis and LearningPreprint
Huang, R., Achlioptas, P., Guibas, L. J., & Ovsjanikov, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03967 · Cited by 1
“Although in most cases the presence of a shape template is assumed to be given a priori, simultaneous template construction and fitting techniques have been used for both reconstruction [Tong et al. 2012; Wand et al. 2009, 2007] and exploration [Kim et al. 2013], among many others.”
MethodSelf-citationSpectral Unions of Partial Deformable 3D Shapes.Preprint
Moschella, L., Melzi, S., Cosmo, L., Maggioli, F., Litany, O., Ovsjanikov, M., Guibas, L. J., & Rodolà, E. (2021) · arXiv (Cornell University) · Cited by 1
Self-citationAutomatic and Self-adaptive Facial Expression Tracking
Chi, J. (2010) · Lecture notes in electrical engineering · doi:10.1007/978-90-481-9794-1_42
3D Motion Completion in Crowded Scenes
Gafni, N., & Sharf, A. (2014) · Computer Graphics Forum · doi:10.1111/cgf.12432
Non-rigid Registration with Reliable Distance Field for Dynamic Shape Completion
Fujiwara, K., Kawasaki, H., Sagawa, R., Ogawara, K., & Ikeuchi, K. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.111
“[23] attempt to form a hierarchy of frame pairs and merge the pairs of shapes.”
BackgroundA 3D Facial Expression Tracking Method Using Piecewise Deformations
Chi, J., Wu, X., Wu, X., & Gao, S. (2013) · Research Journal of Applied Sciences Engineering and Technology · doi:10.19026/rjaset.5.4942
“(2008) and Wand et al .”
Seo, H. (2015) · Human-computer interaction series · doi:10.1007/978-3-319-19947-4_5
Shape analysis of defect-laden data
Silva, C. T., & Berger, M. (2013)
Spatial Matching of Animated Meshes
Seo, H., & Cordier, F. (2016) · Computer Graphics Forum · doi:10.1111/cgf.13000
“Indeed, it is only recently that techniques enabling densely sampled dynamic shape capture start to appear [MFO ∗ 07] [WAO ∗ 09] [WLVGP09].”
BackgroundImage retargeting based on multi-operator
Zhang, Z., Kang, B., & Li, H. (2013) · IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) · doi:10.1109/iccic.2013.6724214
Ciucanu, A., Bhandari, N., Wu, X., Ravikumar, S., Yang, Y., & Cosker, D. P. (2018) · Motion in Games · doi:10.1145/3274247.3274505
“[35] present an efficient pipeline for animation reconstruction, which involves the minimization of an energy term considering distances between data points, acceleration and velocity, volume change and surface smoothness.”
MethodA non-rigid dynamic scene reconstruction method based on surface element model
Jiang, Y. D., Zeng, Y., Du, J., & Fei, W. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739502
Non-rigid registration with reliable distance field for dynamic shape completion
Fujiwara, K., Kawasaki, H., Sagawa, R., Ogawara, K., & Ikeuchi, K. (2014) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2014.7226750
Fast 3D Reconstruction of Human Figures in Motion
Nasir, T. (2018) · doi:10.22215/etd/2018-13395
Scanner Method For Modeling and Manufacturing of 3d Printable Upper Limb Orthosis
Joudah, M. S., Kadhim, F. M., & Hasan, S. F. (2023) · Al-Sadiq International Conference on Communication and Information Technology (AICCIT) · doi:10.1109/aiccit57614.2023.10218181
“Take pictures in the photogrammetry method [19].”
MethodBudria, A., Lopez-Rodriguez, A., Lorente, Ò., & Moreno-Noguer, F. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0960-4_16
Domain Crossover Non-Rigid Registration for 3D Human Meshes
Lee, K., Kim, S., Tong, H., Lee, H., Lee, S., Lin, W., An, P., & Lee, S. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754705
“For partial visibility scenarios, Wand et al. [41] proposed a statistical non-linear optimization framework that robustly aligns scans across topology changes.”
Metadata
- Authors
- Wand, M., Adams, B., Ovsjanikov, M., Berner, A., Bokeloh, M., Jenke, P., Guibas, L., Seidel, H.-P., & Schilling, A.
- Affiliations
- Max Planck Institute for Informatics (DE)
- Stanford University (US)
- University of Tübingen (DE)
- Venue
- ACM Transactions on Graphics
- Published
- 2009-04
- Volume
- 28
- Issue
- 2
- Pages
- 1-15
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W2065270678
- Cited by
- 136
- References
- 64
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 3 · 2023: 5 · 2022: 3 · 2021: 5 · 2020: 4 · 2019: 6 · 2018: 15 · 2017: 6 · 2016: 12 · 2015: 10 · 2014: 14 · 2013: 15 · 2012: 14
- FWCI
- 11.79
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Graphics (publishedVersion)
- Max Planck Institute for Plasma Physics (submittedVersion)
- MPG.PuRe (Max Planck Society) (submittedVersion)
- Funders
- Defense Advanced Research Projects Agency (HR0011-05-1-0007)
- National Science Foundation (ITR 0205671FRG 0354543)
- National Institutes of Health (GM -072970)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- deformation field estimation, 3D scanning, unstructured point clouds, shape fitting, noise and outlier removal, dense correspondence, real-time 3D scanning
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
