The impact of stylization on face recognition

Olivier, Nicolas; Hoyet, Ludovic; Danieau, Fabien; Argelaguet, Ferran; Avril, Quentin; Lécuyer, Anatole; Guillotel, Philippe; Multon, Franck

doi:10.1145/3385955.3407930

Cited by 3 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These artists have the ability to capture distinct facial features, and then exaggerate those features (Redman, 1984). With the development of social VR networks or games, users may wish to use stylized avatars, including avatars preserving their identity (Olivier et al, 2020) but with such exaggerated features. Hence, automatically generating such caricatured avatars becomes a key issue, as having artists manually creating caricatured avatars would not be feasible for such applications involving large numbers of users.…”

Section: Introductionmentioning

confidence: 99%

Study on Automatic 3D Facial Caricaturization: From Rules to Deep Learning

Olivier

Kerbiriou

Arguelaguet

et al. 2022

Front. Virtual Real.

Self Cite

View full text Add to dashboard Cite

Facial caricature is the art of drawing faces in an exaggerated way to convey emotions such as humor or sarcasm. Automatic caricaturization has been explored both in the 2D and 3D domain. In this paper, we propose two novel approaches to automatically caricaturize input facial scans, filling gaps in the literature in terms of user-control, caricature style transfer, and exploring the use of deep learning for 3D mesh caricaturization. The first approach is a gradient-based differential deformation approach with data driven stylization. It is a combination of two deformation processes: facial curvature and proportions exaggeration. The second approach is a GAN for unpaired face-scan-to-3D-caricature translation. We leverage existing facial and caricature datasets, along with recent domain-to-domain translation methods and 3D convolutional operators, to learn to caricaturize 3D facial scans in an unsupervised way. To evaluate and compare these two novel approaches with the state of the art, we conducted the first user study of facial mesh caricaturization techniques, with 49 participants. It highlights the subjectivity of the caricature perception and the complementarity of the methods. Finally, we provide insights for automatically generating caricaturized 3D facial mesh.

show abstract

Section: Introductionmentioning

confidence: 99%

Study on Automatic 3D Facial Caricaturization: From Rules to Deep Learning

Olivier

Kerbiriou

Arguelaguet

et al. 2022

Front. Virtual Real.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Variations of the 3D face shape are based on several factors, including identity, pose, expression and age. An approach that is successfully able to decompose faces into these factors of variations would bring a better understanding of the face semantic, and eventually improve many applications such as expression transfer, expression extrapolation, performance retargeting, avatar creation [10] and personalization [41], facial recognition, or aging and de-aging. This work focuses on two factors: the identity and the expression.…”

Section: Introductionmentioning

confidence: 99%

FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks

Olivier¹,

Baert²,

Danieau³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-toimage translation networks, that have successfully been used in the 2D domain, to 3D face geometry. Leveraging recently released large face scan databases, a neural network has been trained to decouple factors of variations with a better knowledge of the face, enabling facial expressions transfer and neutralization of expressive faces. Specifically, we design an adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations. Using two publicly available datasets (FaceScape and CoMA), FaceTuneGAN has a better identity decomposition and face neutralization than state-of-the-art techniques. It also outperforms classical deformation transfer approach by predicting blendshapes closer to ground-truth data and with less of undesired artifacts due to too different facial morphologies between source and target.

show abstract

Impact of Self-Contacts on Perceived Pose Equivalences

Basset

Ouannas

Hoyet

et al. 2022

Proceedings of the 15th ACM SIGGRAPH Conference on Motion, Interaction and Games

Self Cite

View full text Add to dashboard Cite

Defining equivalences between poses of different human characters is an important problem for imitation research, human pose recognition and deformation transfer. However, pose equivalence is a subjective information that depends on context and on the morphology of the characters. A common hypothesis is that interactions between body surfaces, such as self-contacts, are important attributes of human poses, and are therefore consistently included in animation approaches aiming at retargeting human motions. However, some of these self-contacts are only present because of the morphology of the character and are not important to the pose, e.g. contacts between the upper arms and the torso during a standing A-pose. In this paper, we conduct a first study towards the goal of understanding the impact of self-contacts between body surfaces on perceived pose equivalences. More specifically, we focus on contacts between the arms or hands and the upper body, which are frequent in everyday human poses. We conduct a study where we present to observers two models of a character mimicking the pose of a source character, one with the same self-contacts as the source, and one with one self-contact removed, and ask observers to select which model best mimics the source pose. We show that while poses with different self-contacts are considered different by ob-

show abstract

The impact of stylization on face recognition

Cited by 3 publications

References 32 publications

Study on Automatic 3D Facial Caricaturization: From Rules to Deep Learning

Study on Automatic 3D Facial Caricaturization: From Rules to Deep Learning

FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks

Impact of Self-Contacts on Perceived Pose Equivalences

Contact Info

Product

Resources

About