Optical Flow Constraints on Deformable Models with Applications to Face Tracking

By D. DeCarlo, Dimitris N. Metaxas. International Journal of Computer Vision, 2000

359 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/8e8aa06aa2125008a1baea0dafb4a945892abe61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Face transfer with multilinear models (2005, methodology): “Similar factorizations are also relied upon to separate variations due to pose and lighting, pose and expression, identity and lighting, or style and content in general [Freeman and Tenenbaum 1997; Bregler et al. 2000; DeCarlo and Metaxas 2000; Georghiades et al. 2001; Cao et al. 2003].”
High resolution passive facial performance capture (2010, background): “It is well-known that optical-flow based tracking methods suffer from accumulation of error, known as drift [DeCarlo and Metaxas 2000; Borshukov et al. 2003].”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, methodology): “Since then, different methods for manual [DM00, TDlTM11] deformation.”
OFF-ApexNet on Micro-expression Recognition System (2018, background): “Apart from LBPTOP, optical ﬂow [35] is one of the most popular feature extractors, as it has been very successful in a variety of computer vision tasks, such as action recognition [36], face tracking [37], medical image reconstruction [38].”
Realtime facial animation with on-the-fly correctives (2013, methodology): “Purely video-based facial tracking systems that do not require any markers are aimed at fully uncontrolled environments where a 2D parametric shape model is used [Li et al. 1993; Bregler and Omohundro 1994; Black and Yacoob 1995; Essa et al. 1996; Bregler et al. 1997; Pighin et al. 1999; Decarlo and”
Kernel-Based Object Tracking (2003, background): “For example, face tracking in a crowded scene relies more on target representation than on target dynamics [21], while in aerial video surveillance, e.”
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results (2015, methodology): “The performance of non-rigid dense facial tracking methodologies was usually assessed by using markers [19], simulated data [50], visual inspection [19, 21, 20, 65, 50, 26] or indirectly by the use of the dense facial motion for certain tasks, such as expression analysis [20, 65, 26].”
Head Pose Estimation in Computer Vision: A Survey (2009, neutral): “Some examples include tracking the head with a manually initialized cylindrical model and recursive leastsquares optimization [14], or by tracking with a deformable anthropomorphic 3D model [21].”