Face Recognition Based on Fitting a 3D Morphable Model

By Volker Blanz, Thomas Vetter. 2003

2,282 citations recorded by the source corpus.

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 to generate chairs with convolutional neural networks (2014, background): “Modeling of viewpoint variation is often considered in the context of pose-invariant face recognition [3, 34].”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, background): “The shape priors are typically encoded in the form of simple 3D primitives as demonstrated by early pioneering works [19,20] or learned from rich repositories of 3D CAD models [21,22,23], whereby the concept of fitting 3D models to images of faces was explored to a much larger extent [24,25,26].”
Category-specific object reconstruction from a single image (2014, background): “Note that we learn such models from silhouettes and this is what enables us to learn deformable models without relying on point correspondences between scanned 3D exemplars [8].”
Multi-view 3D Models from Single Images with a Convolutional Network (2015, background): “For example, morphable 3D models [16], [17] are commonly used for faces.”
Learning 3D Object Categories by Looking Around Them (2017, methodology): “Morphable models have sometimes been used [45, 16], particularly for modeling faces [3, 20].”
3D Morphable Face Models—Past, Present, and Future (2019, positive): “General pseudo-second-order methods such as BFGS have been used [Cao et al. 2013; Weise et al. 2011a] as well as genuine second-order methods, specifically a stochastic variant of Newton’s method [Blanz and Vetter 2003].”
Matching 2.5D face scans to 3D models (2006, background): “Because the human face is a threedimensional (3D) object whose 2D projection (image or appearance) is sensitive to the above changes, utilizing 3D face information can improve the face recognition performance [15], [14].”
Nonlinear 3D Face Morphable Model (2018, methodology): “Besides 3DMM fitting methods [5, 15, 35, 44], recently, Richardson et al.”
Face detection, pose estimation, and landmark localization in the wild (2012, methodology): “Most methods use explicit 3D models [6, 17] or 2D view-based models [30, 10, 21].”
Accelerating 3D deep learning with PyTorch3D (2019, background): “There is a vast line of work on 3D shape prediction, including two-view and multiview methods [51, 18], modelbased approaches [13, 5, 4, 35, 3, 33], and recent supervised deep methods that predict voxels [8, 55], meshes [17, 59, 54, 14], point clouds [11] and implicit functions [37, 42, 50].”
Detecting People Looking at Each Other in Videos (2013, background): “1; and, (iii) the length of the temporal window W in the range [5,11] in steps of 2.”
Frontal to profile face verification in the wild (2016, methodology): “This line of work started in [4] and exploded as a general model fitting technique; for example Generic Elastic Models (GEM) [25] and Active Appearance based Models for Pose normalization [2].”
Deep Face Recognition: A Survey (2018, methodology): “[155] directly regressed 3D morphable face model (3DMM) [16] parameters from an input photo by a very deep CNN architecture.”
FSGAN: Subject Agnostic Face Swapping and Reenactment (2019, neutral): “Transfer is performed by ﬁtting a 3D morphable face model (3DMM) [5, 7, 11] to both faces and then applying the expression components of one face onto the other with care given to interior mouth regions.”
Elected in 100 milliseconds: Appearance-Based Trait Inferences and Voting (2010, neutral): “Specifically, Oosterhof and Todorov used a statistical model for representing face shape, in which faces are represented as points in a multi-dimensional space ( Blanz and Vetter 1999, 2003; Singular Inversions 2006).”
Face recognition: A literature survey (2003, methodology): “21One exception is a recent report [Blanz and Vetter 2003] where faces were represented using 4448 images from the CMU-PIE databases and 1940 images from the FERET database.”
50 years of biometric research: Accomplishments, challenges, and opportunities (2016, neutral): “Consequently , most of the research in biometric recognition has rightly focused on the following two fundamental problems:”
Names and faces in the news (2004, background): “Early face recognition is done in [19, 21] and is reviewed in [12, 6, 13].”