A morphable model for the synthesis of 3D faces

By Marco Nef, Volker Blanz, Thomas Vetter. 1999

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

FAME-a flexible appearance modeling environment (2003, methodology): “In this case a hierarchical approach [47] should be used to increase segmentation accuracy.”
SofGAN: A Portrait Image Generator with Dynamic Styling (2020, background): “…approaches explore to achieve controllable image synthesis by disentangling the generation space into semantically meaningful attributes, either based on vector arithmetic phenomenon [Collins et al. 2020; Shen et al. 2019] or shape priors [Tewari et al. 2020] such as 3DMM [Blanz and Vetter 1999].”
Analysis of human faces using a measurement-based skin reflectance model (2006, background): “Other researchers have estimated parameters of uniform analytic BRDF models from photographs with static [Blanz and Vetter 1999; Paris et al. 2003] or varying illumination [Georghiades 2003; Fuchs et al. 2005b].”
Text-based editing of talking-head video (2019, methodology): “Many of these techniques employ a parametric face model[Blanz et al. 2004; Blanz and Vetter 1999; Booth et al. 2018] as a prior to better constrain the reconstruction problem.”
Modular primitives for high-performance differentiable rendering (2020, methodology): “Many methods utilize morphable 3D models [Blanz and Vetter 1999] that enable approximating the facial geometry even from monocular data.”
Single image portrait relighting (2019, background): “FaceReconstructionandRelighting: Usingamorphablemodel of faces allows for relighting under certain circumstances [Blanz and Vetter 1999].”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “Finally, the identity is retained by using a novel landmark transformer, influenced by the 3DMM facial model [135].”
PIE (2020, methodology): “To overcome this limitation, StyleRig [Tewari et al. 2020] describes a neural network that maps the parameters of a 3D morphable face model (3DMM) [Blanz and Vetter 1999] to a pretrained StyleGAN 1 For example: www.adobe.com/Photoshop for face images.”
paGAN (2018, unknown): “The work of [Blanz and Vetter 1999] is the first instance of learning a 3D PCA model of face shape and texture, using around 200 subjects in neutral poses.”
Deep video portraits (2018, methodology): “We represent the space of facial identity based on a parametric head model [Blanz and Vetter 1999], and the space of facial expressions via an aine model.”
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (2022, methodology): “For expression, we design a novel audio to expression coefficient network by distilling the coefficients from the lip motion only coefficients from [28] and the perceptual losses (lip-reading loss [1], facial landmark loss) on the reconstructed rendered 3D face [5].”
Deep appearance models for face rendering (2018, methodology): “…Models (AAMs) [Cootes et al. 2001; Edwards et al. 1998; Matthews and Baker 2004; Tzimiropoulos et al. 2013] and 3D morphable models (3DMM) [Blanz and Vetter 1999; Knothe et al. 2011] have been used as an effective way to register faces in images through analysis-by-synthesis using a low…”
Towards Fast, Accurate and Stable 3D Dense Face Alignment (2020, background): “We first discuss 3D Morphable Model (3DMM) [5].”
Transformed Social Interaction: Decoupling Representation from Behavior and Form in Collaborative Virtual Environments (2004, methodology): “This similarity could be achieved in various manners, employing any of a number of techniques to parametrically vary the similarity of computer-generated models via 2D and 3D morphing techniques (Blanz & Vetter, 1999; Busey, 1998; Decarlo, Metaxas, & Stone, 1998).”
Neural Voice Puppetry: Audio-driven Facial Reenactment (2019, methodology): “3D Face Tracking: Our method is using a statistical face model and delta-blendshapes [1, 28] to represent a 3D latent space for modelling facial animation.”