A Morphable Model For The Synthesis Of 3D Faces

By Volker Blanz, Thomas Vetter. 1999

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Learning Descriptor Networks for 3D Shape Synthesis and Analysis (2018, background): “Researchers in the ﬁelds of graphics and vision have studied the 3D object synthesis problems [2, 3, 9].”
Deep Convolutional Inverse Graphics Network (2015, methodology): “Vetter et al.[5] ﬁrst proposed using 3D laser scanned face data to learn a deformable 3D face model (3DMM).”
A Hybrid Model for Identity Obfuscation by Face Replacement (2018, methodology): “. and represent the shape and re ectance of the face, and correspond to the identity of the person. These parameters are the coecients of the PCA vectors constructed from 200 high-quality face scans [10]. are the coecients of the expression basis vectors computed using PCA on selected blend shapes o”
Generating 3D faces using Convolutional Mesh Autoencoders (2018, background): “Blanz and Vetter [2] introduced the morphable model ; the first generic representation for 3D faces based on principal component analysis (PCA) to describe facial shape and texture variations.”
Learning Category-Specific Mesh Reconstruction from Image Collections (2018, background): “Pioneering work of Blanz and Vetter [2] extended these ideas to 3D shapes to model the space of faces.”
Learning a Multi-View Stereo Machine (2017, methodology): “Learning has been used for multi-view reconstruction in the form of shape priors for objects [2, 9, 58, 20, 27, 52], or semantic class speciﬁc surface priors for scenes [22, 17, 45].”
Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency (2017, background): “Blanz and Vetter [1] demonstrated the use of a morphable model to capture 3D shapes.”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, background): “[1] propose to build a morphable shape model for faces, which allows for the reconstruction of faces from just a single image.”
3D Shape Induction from 2D Views of Multiple Objects (2016, methodology): “This makes it difﬁcult to apply exisiting approaches of estimating geometry based on structure from motion [12, 4], or computing visual hulls [18].”
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (2016, methodology): “, 2011, Blanz and Vetter, 1999, Kalogerakis et al., 2012, Chaudhuri et al., 2011, Xue et al., 2012, Kar et al., 2015, Bansal et al., 2016, Wu et al., 2016]. Since decades ago, AI and vision researchers have made inspiring attempts to design or learn 3D object representations, mostly based on meshes ”
Lifting Object Detection Datasets into 3D (2015, positive): “To account for differences between the 3D exemplars and the object depicted, Su and Guibas [26] choose a few exemplars that appear to be similar to the depicted shape and combine them to produce a single depth map.”
Category-specific object reconstruction from a single image (2014, positive): “Here we pursue more expressive basis shape models [1, 7, 42] which establish a balance between the two extremes as they can deform but only along class-specific modes of variation.”
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis (2015, methodology): “We tune the K value in [1,3,5,7], namely KNN1, KNN3, KNN5 and KNN7 to achieve the best performance.”
Deformable Shape Completion with Graph Convolutional Autoencoders (2017, background): “A viable alternative is model-based approaches, where a parametric morphable model describing the variability of a certain class of objects can be fit to the observed data [4, 16].”
Face recognition across pose: A review (2009, methodology): “Blanz and Vetter [13,14] proposed a successful face recognition system using 3D morphable model based on image-based reconstruction and prior knowledge of human faces.”
Multiple Object Response Normalization in Monkey Inferotemporal Cortex (2005, methodology): “Faces were built using a face-morphing algorithm (Blanz and Vetter, 1999), in which point correspondences between pairs of face prototypes were established based on the three-dimensional structure of the head models.”
View-Invariant Recognition Using Corresponding Object Fragments (2004, background): “[ 6 ]). Due to this requirement, recognition using 3D data is frequently considered separately from image-based methods.”
Modeling object appearance using Context-Conditioned Component Analysis (2015, background): “The Morphable Model [2] extended the AAM into 3D for modeling faces which also helps with occlusions; however, it still cannot handle varying numbers of parts and requires alignment to a template.”