Efficient, robust and accurate fitting of a 3D morphable model
Abstract
3D morphable models, as a means to generate images of a class of objects and to analyze them, have become increasingly popular. The problematic part of this framework is the registration of the model to an image, a.k.a. the fitting. The characteristic features of a fitting algorithm are its efficiency, robustness, accuracy and automation. Many accurate algorithms based on gradient descent techniques exist which are unfortunately short on the other features. Recently, an efficient algorithm called inverse compositional image alignment (ICIA) algorithm, able to fit 2D images, was introduced. We extent this algorithm to fit 3D morphable models using a novel mathematical notation which facilitates the formulation of the fitting problem. This formulation enables us to avoid a simplification so far used in the ICIA, being as efficient and leading to improved fitting precision. Additionally, the algorithm is robust without sacrificing its efficiency and accuracy, thereby conforming to three of the four characteristics of a good fitting algorithm.
Integrity signals
Registry
Cites
Statistics
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?
3D versions of AAM make alignment much slower due to the impossibility of decoupling shape and appearance fitting.
“3D versions of AAM have also been proposed [78], but making alignment much slower due to the impossibility of decoupling shape and appearance fitting.”
From Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-Related Applications (2016) · cites this paper as [78]
Cites
Huber, P. J. (1981) · Wiley Series in Probability and Statistics · doi:10.1002/0471725250 · Cited by 7,066 · see citing works
A morphable model for the synthesis of 3D faces
Blanz, V., & Vetter, T. R. (1999) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/311535.311556 · Cited by 4,695 · see citing works
Levary, R. R. (1982) · European Journal of Operational Research · doi:10.1016/0377-2217(82)90093-5 · Cited by 4,170 · see citing works
Low-dimensional procedure for the characterization of human faces
Sirovich, L., & Kirby, M. J. L. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.000519 · Cited by 2,329 · see citing works
Robust regression using iteratively reweighted least-squares.
Holland, P. W., & Welsch, R. E. (1977) · Communications in Statistics - Theory and Methods · doi:10.1080/03610927708827533 · Cited by 2,115 · see citing works
Visual learning and recognition of 3-d objects from appearance
Murase, H., & Nayar, S. K. (1995) · International Journal of Computer Vision · doi:10.1007/bf01421486 · Cited by 1,873 · see citing works
View-based and modular eigenspaces for face recognition
Pentland, Moghaddam, & Starner (1994) · doi:10.1109/cvpr.1994.323814 · Cited by 1,806 · see citing works
Efficient region tracking with parametric models of geometry and illumination
Hager, G. D., & Belhumeur, P. N. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.722606 · Cited by 1,066 · see citing works
Linear object classes and image synthesis from a single example image
Vetter, T., & Poggio, T. (1997) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.598230 · Cited by 410 · see citing works
Equivalence and efficiency of image alignment algorithms
Baker, S. J., & Matthews, I. A. (2005) · 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.2001.990652 · Cited by 408 · see citing works
Face identification across different poses and illuminations with a 3D morphable model
Blanz, V., Romdhani, S., & Vetter, T. (2003) · doi:10.1109/afgr.2002.1004155 · Cited by 301 · see citing works
View-based active appearance models
Cootes, T. F., Walker, K., & Taylor, C. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.2000.840639 · Cited by 250 · see citing works
Face Identification by Fitting a 3D Morphable Model Using Linear Shape and Texture Error Functions
Romdhani, S., Blanz, V., & Vetter, T. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47979-1_1 · Cited by 217 · see citing works
Integrating a Robust Option into a Multiple Regression Computing Environment
DuMouchel, W., & O’Brien, F. (1991) · The IMA volumes in mathematics and its applications · doi:10.1007/978-1-4613-9154-8_3 · Cited by 185 · see citing works
Separability of pose and expression in facial tracking and animation
Bascle, B., & Blake, A. (2002) · International Conference on Computer Vision · doi:10.1109/iccv.1998.710738 · Cited by 89 · see citing works
A Simple Method for Robust Regression
Hinich, M. J., & Talwar, P. P. (1975) · Journal of the American Statistical Association · doi:10.1080/01621459.1975.10480271 · Cited by 86 · see citing works
Craw, I., & Cameron, P. (1992) · Springer eBooks · doi:10.1007/978-1-4471-3201-1_52 · Cited by 73 · see citing works
Parameterising Images for Recognition and Reconstruction
Craw, I., & Cameron, P. J. (1991) · Springer eBooks · doi:10.1007/978-1-4471-1921-0_52 · Cited by 71 · see citing works
Gaze estimation using morphable models
Rikert, T. D., & Jones, M. (2002) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/afgr.1998.670987 · Cited by 52 · see citing works
Craw, I., & Cameron, P. M. N. (1992) · British Machine Vision Conference (BMVC) · doi:10.5244/c.6.52 · Cited by 21 · see citing works
Learning-Based Approach to Estimation of Morphable Model Parameters
Kumar, V. P., & Poggio, T. (2000) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Corneanu, C. A., Simon, M. O., Cohn, J. F., & Guerrero, S. E. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2515606 · Cited by 527 · see citing works
Static and dynamic 3D facial expression recognition: A comprehensive survey
Sandbach, G., Zafeiriou, S., Pantic, M., & Yin, L. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.06.005 · Cited by 357 · see citing works
- Authors
- Romdhani, & Vetter
- Affiliations
- University of Basel (CH)
- Venue
- Proceedings Ninth IEEE International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2003
- Pages
- 59-66 vol.1
- OpenAlex
- W2097365005
- Cited by
- 189
- References
- 21
- Citations by year
- 2025: 2 · 2023: 3 · 2022: 5 · 2021: 4 · 2020: 6 · 2019: 9 · 2018: 11 · 2017: 8 · 2016: 9 · 2015: 6 · 2014: 7 · 2013: 4 · 2012: 16
- FWCI
- 9.10
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- IEEE/CVF International Conference on Computer Vision (ICCV)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Keywords
- 3D morphable model, model fitting, shape registration, facial shape modeling, robustness, fitting accuracy
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
