Three-Dimensional Face Caricaturing by Anthropometric Distortions

Vieira, Roberto Cesar Cavalcante; Vidal, Creto Augusto; Cavalcante-Neto, Joaquim Bento

doi:10.1109/sibgrapi.2013.31

Cited by 13 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Creating 3D face models in this style is also a popular topic in computer graphics. A common approach exaggerates an input 3D model by magnifying the differences between the input model and a reference model ( (Lewiner et al 2011;Vieira et al 2013)) through deformation. Sela et al (2015) considered gradients as a measure of characteristics and proposed a method to perform exaggeration by scaling the gradients at mesh vertices.…”

Section: Initial Sketching Mode Gesture-based Refinement Follow-up Sk...mentioning

confidence: 99%

DeepSketch2Face

2017

View full text Add to dashboard Cite

Fig. 1. Using our sketching system, an amateur user can create 3D face or caricature models with complicated shape and expression in a few minutes. Both models shown here were created in less than 10 minutes by a user without any prior drawing and modeling experiences.Face modeling has been paid much attention in the field of visual computing. There exist many scenarios, including cartoon characters, avatars for social media, 3D face caricatures as well as face-related art and design, where low-cost interactive face modeling is a popular approach especially among amateur users. In this paper, we propose a deep learning based sketching system for 3D face and caricature modeling. This system has a labor-efficient sketching interface, that allows the user to draw freehand imprecise yet expressive 2D lines representing the contours of facial features. A novel CNN based deep regression network is designed for inferring 3D face models from 2D sketches. Our network fuses both CNN and shape based features of the input sketch, and has two independent branches of fully connected layers generating independent subsets of coefficients for a bilinear face representation. Our system also supports gesture based interactions for users to further manipulate initial face models. Both user studies and numerical results indicate that our sketching system can help users create face models quickly and effectively. A significantly expanded face database with diverse identities, expressions and levels of exaggeration is constructed to promote further research and evaluation of face modeling techniques.

show abstract

Section: Initial Sketching Mode Gesture-based Refinement Follow-up Sk...mentioning

confidence: 99%

DeepSketch2Face

2017

View full text Add to dashboard Cite

show abstract

“…Some methods utilize sketches as the prior condition for generation 22,23 . Other methods are guided by position and landmarks, extracting human facial features used to deform textures and meshes [24][25][26][27] . Recently a conditional GAN has been applied in the generation process 28,29 .…”

Section: Related Workmentioning

confidence: 99%

Tag-based annotation creates better avatars

Liu

Cheng

Shen

et al. 2023

Preprint

View full text Add to dashboard Cite

Avatar creation from human images allows users to customize their digital figures in different styles. Existing rendering systems like Bitmoji, MetaHuman, and Google Cartoonset provide expressive rendering systems that serve as excellent design tools for users. However, twenty-plus parameters, some including hundreds of options, must be tuned to achieve ideal results. Thus it is challenging for users to create the perfect avatar. A machine learning model could be trained to predict avatars from images, however the annotators who label pairwise training data have the same difficulty as users, causing high label noise. In addition, each new rendering system or version update requires thousands of new training pairs. In this paper, we propose a Tag-based annotation method for avatar creation. Compared to direct annotation of labels, the proposed method: produces higher annotator agreements, causes machine learning to generates more consistent predictions, and only requires a marginal cost to add new rendering systems.

show abstract

“…This is typically implemented by detecting distinctive facial features and then exaggerating them on the face mesh using deformation techniques. Some methods [31], [32] exaggerate an input 3D model by magnifying the differences between the input model and a template model while some works [33], [34] attempt to model 3D caricatures from 2D images. Recently, some deep learning-based interactive systems [35], [36] are proposed for modeling 3D caricature faces by interactively drawing sketches.…”

Section: D Style Transfermentioning

confidence: 99%

Exemplar-Based 3D Portrait Stylization

Han

et al. 2021

Preprint

View full text Add to dashboard Cite

Exemplar-based portrait stylization is widely attractive and highly desired. Despite recent successes, it remains challenging, especially when considering both texture and geometric styles. In this paper, we present the first framework for one-shot 3D portrait style transfer, which can generate 3D face models with both the geometry exaggerated and the texture stylized while preserving the identity from the original content. It requires only one arbitrary style image instead of a large set of training examples for a particular style, provides geometry and texture outputs that are fully parameterized and disentangled, and enables further graphics applications with the 3D representations. The framework consists of two stages. In the first geometric style transfer stage, we use facial landmark translation to capture the coarse geometry style and guide the deformation of the dense 3D face geometry. In the second texture style transfer stage, we focus on performing style transfer on the canonical texture by adopting a differentiable renderer to optimize the texture in a multi-view framework. Experiments show that our method achieves robustly good results on different artistic styles and outperforms existing methods. We also demonstrate the advantages of our method via various 2D and 3D graphics applications. Project page is: https://halfjoe.github.io/projs/3DPS/index.html.

show abstract

Three-Dimensional Face Caricaturing by Anthropometric Distortions

Cited by 13 publications

References 11 publications

DeepSketch2Face

DeepSketch2Face

Tag-based annotation creates better avatars

Exemplar-Based 3D Portrait Stylization

Contact Info

Product

Resources

About