Face identification across different poses and illuminations with a 3D morphable model

By Volker Blanz, Sami Romdhani, Thomas Vetter. Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, 2002

370 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/23fcdda2d12c982bcc0abb948ff835c370b8d75e

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

Describable Visual Attributes for Face Verification and Image Search (2011, neutral): “These manifold differences in images of the same person have confounded methods for automatic face recognition and verification, often limiting the reliability of automatic algorithms to the domain of more controlled settings with cooperative subjects [4], [22], [24], [45], [47], [50], [52].”
Probabilistic Linear Discriminant Analysis for Inferences About Identity (2007, background): “Important categories include algorithms which (i) require more than one input image of each face [8] (ii) create a 3D model from the 2D image and estimate pose and lighting explicitly [ 3 , 2] and (iii) learn a statistical relation between faces viewed under different conditions [9, 12].”
Learning an animatable detailed 3D face model from in-the-wild images (2020, methodology): “Such methods can be categorized into optimization-based [Aldrian and Smith 2013; Bas et al. 2017; Blanz et al. 2002; Blanz and Vetter 1999; Gerig et al. 2018; Romdhani and Vetter 2005; Thies et al. 2016], or learning-based methods [Chang et al. 2018; Deng et al. 2019; Genova et al. 2018; Kim et al.…”
Extreme 3D Face Reconstruction: Looking Past Occlusions (2017, methodology): “The first goal, exemplified by early 3D morphable models (3DMM) [2, 5, 33], some later shape from shading (SfS) techniques [25, 27], and several recent deep learning methods [36, 39], is obtaining highly detailed 3D face shapes.”
Component-Based Face Recognition with 3D Morphable Models (2003, background): “A system for view and illumination invariant face recognition from single video images has recently been proposed in [1].”
Appearance-based face recognition and light-fields (2004, methodology): “exemplified by Active Appearance Models [10] and 3D Morphable Models [ 9 , 24].”
Regressing Robust and Discriminative 3D Morphable Models with a Very Deep Neural Network (2016, background): “The highly successful 3D Morphable Models (3DMM), for example, were only ever used for recognition in limited, controlled viewing conditions [4, 7, 11, 17, 28].”
EMOCA: Emotion Driven Monocular Face Capture and Animation (2022, methodology): “Existing methods can be categorized into optimization-based [4,5,9,10,31,45,63,69,84,90] and learning-based.”
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.”
Face Recognition Based on Fitting a 3D Morphable Model (2003, methodology): “This makes intrinsic shape and texture fully independent of extrinsic parameters [8], [7].”
An Image Preprocessing Algorithm for Illumination Invariant Face Recognition (2003, background): “[9] fit a previously constructed morphable 3D model to single images.”
Face recognition in hyperspectral images (2003, methodology): “A 3D morphable face model has been used for face identification across different poses [16].”
Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model image (2005, methodology): “There are a number of conventional techniques that have been developed for view-invariant face recognition [4], [6], [10], [12], [13], [15], [25], [26], [28].”
Recent advances in visual and infrared face recognition - a review (2005, background): “FRVT 2002 addressed several important face recognition topics and the impact of new techniques for improving face recognition: 3D morphable models [70,71], normalization of similarity scores, and face recognition from video sequences.”
Extreme 3D Face Reconstruction: Seeing Through Occlusions (2017, methodology): “We use the standard, linear 3DMM representation of 3D faces [1, 4, 10, 19, 35].”