We describe a deep learning based method for estimating 3D facial expression coefficients. Unlike previous work, our process does not relay on facial landmark detection methods as a proxy step. Recent methods have shown that a CNN can be trained to regress accurate and discriminative 3D morphable model (3DMM) representations, directly from image intensities. By foregoing landmark detection, these methods were able to estimate shapes for occluded faces appearing in unprecedented viewing conditions. We build on those methods by showing that facial expressions can also be estimated by a robust, deep, landmark-free approach. Our ExpNet CNN is applied directly to the intensities of a face image and regresses a 29D vector of 3D expression coefficients. We propose a unique method for collecting data to train our network, leveraging on the robustness of deep networks to training label noise.

ExpNet: Landmark-Free, Deep, 3D Facial Expressions / Chang, Feng-Ju; Tran Anh, Tuan; Hassner, Tal; Masi, I; Nevatia, Ram; Medioni, Gerard. - (2018). ((Intervento presentato al convegno IEEE Conference on Automatic Face and Gesture Recognition (FG) tenutosi a Xian (China).

ExpNet: Landmark-Free, Deep, 3D Facial Expressions

Masi I;
2018

Abstract

We describe a deep learning based method for estimating 3D facial expression coefficients. Unlike previous work, our process does not relay on facial landmark detection methods as a proxy step. Recent methods have shown that a CNN can be trained to regress accurate and discriminative 3D morphable model (3DMM) representations, directly from image intensities. By foregoing landmark detection, these methods were able to estimate shapes for occluded faces appearing in unprecedented viewing conditions. We build on those methods by showing that facial expressions can also be estimated by a robust, deep, landmark-free approach. Our ExpNet CNN is applied directly to the intensities of a face image and regresses a 29D vector of 3D expression coefficients. We propose a unique method for collecting data to train our network, leveraging on the robustness of deep networks to training label noise.
IEEE Conference on Automatic Face and Gesture Recognition (FG)
expression recognition, face analysis, deep learning
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
ExpNet: Landmark-Free, Deep, 3D Facial Expressions / Chang, Feng-Ju; Tran Anh, Tuan; Hassner, Tal; Masi, I; Nevatia, Ram; Medioni, Gerard. - (2018). ((Intervento presentato al convegno IEEE Conference on Automatic Face and Gesture Recognition (FG) tenutosi a Xian (China).
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1458942
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 65
  • ???jsp.display-item.citation.isi??? 50
social impact