Multidimensional morphable models

By Michael J. Jones, Tomaso A. Poggio. 1998

How researchers see this paper

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

Citations in the corpus

Learning-based Video Motion Magnification (2018, methodology): “The encoder acts as a spatial decomposition filter that extracts a shape representation [9] from a single frame, which we can use to manipulate motion (analogous to the phase of the steerable pyramid and Riesz pyramid [24, 25]).”
Monocular Pedestrian Detection: Survey and Experiments (2009, methodology): “Continuous shape models involve a compact parametric representation of the class-conditional density, learned from a set of training shapes, given the existence of an appropriate manual [9], [25], [26] or automatic [4], [5], [14], [34], [50] shape registration method.”
Inferring 3D structure with a statistical image-based shape model (2003, methodology): “The use of linear subspaces estimated by PCA to represent an object class, and more generally an appearance model, has been developed by several authors [3, 10, 16].”
Statistical shape influence in geodesic active contours (2000, methodology): “We are also extending this method to use correspondences (when they are available) to ensure the comparison of “like” pixels instead of “near” pixels using flow fields as in [7].”
Age Synthesis and Estimation via Faces: A Survey (2010, background): “Usually, a large size face database is associated with a generic model considering linear object class [98], [99].”
Statistical models of appearance for medical image analysis and computer vision (2001, methodology): “Jones and Poggio use a model capable of synthesizing faces and describe a stochastic optimisation method to match the model to new face images.(21) The method is slow but can be robust because of the quality of”
Supervised Descent Method and Its Applications to Face Alignment (2013, methodology): “Parameterized Appearance Models (PAMs), such as Active Appearance Models [11, 14, 2], Morphable Mod- els [6, 19], Eigentracking [5], and template tracking [22, 30] build an object appearance and shape representation by computing Principal Component Analysis (PCA) on a set of manually labeled data.”
Active Appearance Models Revisited (2004, methodology): “For example, Levenberg- Marquardt was used in [Sclaroff and Isidoro, 1998] and a stochastic gradient descent algorithm was used in [Jones and Poggio, 1998, Blanz and Vetter, 1999].”
Facial Expression Analysis (2011, methodology): “method [74], Eigentracking [12], Active Appearance Models [28, 34, 87, 33], and Morphable Models [14, 57], that have been popular approaches for facial feature detection, tracking and modeling faces in general.”