Spatial and Temporal Linearities in Posed and Spontaneous Smiles

Abstract

Creating facial animations that convey an animator's intent is a difficult task because animation techniques are necessarily an approximation of the subtle motion of the face. Some animation techniques may result in linearization of the motion of vertices in space (blendshapes, for example), and other, simpler techniques may result in linearization of the motion in time.In this article, we consider the problem of animating smiles and explore how these simplifications in space and time affect the perceived genuineness of smiles. We create realistic animations of spontaneous and posed smiles from high-resolution motion capture data for two computer-generated characters. The motion capture data is processed to linearize the spatial or temporal properties of the original animation. Through perceptual experiments, we evaluate the genuineness of the resulting smiles. Both space and time impact the perceived genuineness. We also investigate the effect of head motion in the perception of smiles and show similar results for the impact of linearization on animations with and without head motion. Our results indicate that spontaneous smiles are more heavily affected by linearizing the spatial and temporal properties than posed smiles. Moreover, the spontaneous smiles were more affected by temporal linearization than spatial linearization. Our results are in accordance with previous research on linearities in facial animation and allow us to conclude that a model of smiles must include a nonlinear model of velocities.

Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction

“…Therefore, reviewing the literature from the perspective of cognitive science might be more informative in order to understand and propose a proper technique for real-fake expression prediction. In particular, [11,26] show that small emotional changes in eyes and mount movements can be used to interpret an expression as genuine (real) or deceptive (fake) from the sequence of faces. This indicates that both spatial interdependencies of face parts and their sequential structure should be considered in the final model.…”

“…For facial emotions, real-fake expression prediction on a video is slightly different from frame-level emotion classification: 1) Temporal interrelations between face parts should be considered, since temporal consistency is highly critical to categorize human expressions [26]. 2) Emotional changes in eyes and mount movements can be distinct to separate real expressions from fake ones [11].…”

Dynamics of facial actions for assessing smile genuineness

“…Automatic recognition of facial expressions from digital images and videos has been explored for years, becoming a multidisciplinary research topic that embraces computer vision, machine learning, psychology, neuroscience, and cognitive sciences. Potential applications of recognizing facial expressions are related with healthcare, surveillance, animation engines, driver safety, creating responsive human-computer interfaces, and more [ 3 ].…”

Dynamic properties of successful smiles

“…Synthetic models of human facial expressions [ 16 – 18 ] offer exciting possibilities for the study of spatial and temporal aspects of dynamic expressions of emotion. Past research has revealed that spatial and temporal characteristics of dynamic facial expressions can be useful for distinguishing between different types of smiles [ 19 , 20 ]. Furthermore, some studies have shown that the dynamics of facial expressions can have important, real-world economic and social outcomes [ 21 , 22 ], and other studies have examined the role of symmetry (or asymmetry) in dynamic facial expressions [ 23 , 24 ].…”