Fast and exact Newton and bidirectional fitting of Active Appearance Models
Active Appearance Models (AAMs) are generative models of shape and appearance that have proven very attractive for their ability to handle wide changes in illumination, pose and occlusion when trained in the wild, while not requiring large training dataset like regression-based or deep learning meth...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers
2016
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/39856/ |
| _version_ | 1848795929726943232 |
|---|---|
| author | Kossaifi, Jean Tzimiropoulos, Georgios Pantic, Maja |
| author_facet | Kossaifi, Jean Tzimiropoulos, Georgios Pantic, Maja |
| author_sort | Kossaifi, Jean |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Active Appearance Models (AAMs) are generative models of shape and appearance that have proven very attractive for their ability to handle wide changes in illumination, pose and occlusion when trained in the wild, while not requiring large training dataset like regression-based or deep learning methods. The problem of fitting an AAM is usually formulated as a non-linear least squares one and the main way of solving it is a standard Gauss-Newton algorithm. In this paper we extend Active Appearance Models in two ways: we first extend the Gauss-Newton framework by formulating a bidirectional fitting method that deforms both the image and the template to fit a new instance. We then formulate a second order method by deriving an efficient Newton method for AAMs fitting. We derive both methods in a unified framework for two types of Active Appearance Models, holistic and part-based, and additionally show how to exploit the structure in the problem to derive fast yet exact solutions. We perform a thorough evaluation of all algorithms on three challenging and recently annotated inthe- wild datasets, and investigate fitting accuracy, convergence properties and the influence of noise in the initialisation. We compare our proposed methods to other algorithms and show that they yield state-of-the-art results, out-performing other methods while having superior convergence properties. |
| first_indexed | 2025-11-14T19:39:54Z |
| format | Article |
| id | nottingham-39856 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:39:54Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-398562020-05-04T18:24:54Z https://eprints.nottingham.ac.uk/39856/ Fast and exact Newton and bidirectional fitting of Active Appearance Models Kossaifi, Jean Tzimiropoulos, Georgios Pantic, Maja Active Appearance Models (AAMs) are generative models of shape and appearance that have proven very attractive for their ability to handle wide changes in illumination, pose and occlusion when trained in the wild, while not requiring large training dataset like regression-based or deep learning methods. The problem of fitting an AAM is usually formulated as a non-linear least squares one and the main way of solving it is a standard Gauss-Newton algorithm. In this paper we extend Active Appearance Models in two ways: we first extend the Gauss-Newton framework by formulating a bidirectional fitting method that deforms both the image and the template to fit a new instance. We then formulate a second order method by deriving an efficient Newton method for AAMs fitting. We derive both methods in a unified framework for two types of Active Appearance Models, holistic and part-based, and additionally show how to exploit the structure in the problem to derive fast yet exact solutions. We perform a thorough evaluation of all algorithms on three challenging and recently annotated inthe- wild datasets, and investigate fitting accuracy, convergence properties and the influence of noise in the initialisation. We compare our proposed methods to other algorithms and show that they yield state-of-the-art results, out-performing other methods while having superior convergence properties. Institute of Electrical and Electronics Engineers 2016-12-21 Article PeerReviewed Kossaifi, Jean, Tzimiropoulos, Georgios and Pantic, Maja (2016) Fast and exact Newton and bidirectional fitting of Active Appearance Models. IEEE Transactions on Image Processing, 26 (2). pp. 1040-1053. ISSN 1941-0042 (In Press) Active Appearance Models Newton method bidirectional image alignment inverse compositional forward additive http://ieeexplore.ieee.org/document/7792677/ doi:10.1109/TIP.2016.2642828 doi:10.1109/TIP.2016.2642828 |
| spellingShingle | Active Appearance Models Newton method bidirectional image alignment inverse compositional forward additive Kossaifi, Jean Tzimiropoulos, Georgios Pantic, Maja Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title | Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title_full | Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title_fullStr | Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title_full_unstemmed | Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title_short | Fast and exact Newton and bidirectional fitting of Active Appearance Models |
| title_sort | fast and exact newton and bidirectional fitting of active appearance models |
| topic | Active Appearance Models Newton method bidirectional image alignment inverse compositional forward additive |
| url | https://eprints.nottingham.ac.uk/39856/ https://eprints.nottingham.ac.uk/39856/ https://eprints.nottingham.ac.uk/39856/ |