Facial caricaturing with motion caricaturing in PICASSO system

Tominaga, Michiaki; Fukuoka, S.; Murakami, Kazuhito; Koshimizu, Hiroyasu

doi:10.1109/aim.1997.652888

Cited by 21 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting work on caricature was presented by Chiang et al [4], which adds exaggeration upon a mesh-based representation for facial geometry (similar to Wang and Tang [21]) instead of the contour-based ones used by Tominaga et al [18,19], Obaid et al [17], and Liang et al [12]. This enables more details in color and texture in the rendered caricature, as shown in Figure 24.…”

Section: Discussionmentioning

confidence: 99%

“…Most caricatures explicitly trade certain degree of fidelity for unique aesthetic effects, for example, by exaggerating features in several parts of the face. Tominaga et al [18,19] developed the PICASSO facial caricaturing system. In the PICASSO system, 445 characteristic points are located on the edges of facial parts, and various expressions are defined as offsets of these points from a mean face (without expression), as shown in Figure 18.…”

Section: Caricaturementioning

confidence: 99%

“…Fig. 18 In PICASSO [18,19], 445 characteristic points with contour lines are used for representing the facial shape, and a static representation of expressions is by offseting these points.…”

Section: Caricaturementioning

confidence: 99%

See 2 more Smart Citations

Artistic Rendering of Portraits

Zhao

Zhu

2012

Computational Imaging and Vision

View full text Add to dashboard Cite

This chapter presents an overview of the latest artistic portrait rendering techniques. Artistic rendering or portraits can be viewed as an image generating process controlled by two factors. The first one is the face fidelity, namely, a rendered portrait image should preserve a certain amount of the original face's information. The second factor is the artistic style, for example, sketch, painting, etc. In the literature, different portrait rendering algorithms either adopt different models and data structures to represent the facial information, or use different graphical elements and compositional methods to simulate various styles. These two factors essentially reveal the two principles in portraiture, namely the pursuit of likeness and aesthetic.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Caricaturementioning

confidence: 99%

See 1 more Smart Citation

Artistic Rendering of Portraits

Zhao

Zhu

2012

Computational Imaging and Vision

View full text Add to dashboard Cite

show abstract

“…Blanz et al [2] applied the difference of the expression and the neutral expression to a 3D facial model, which is then driven by the video to generate the animation. To generate an exaggerated facial image, the warping method was employed [5], which use the feature difference between specific face and the reference face [5] [9]. However, this method involves user's intervention, as well as computing facial triangulation and alignment, therefore, has a low degree of automation and fairly high computational complexity.…”

Section: Introductionmentioning

confidence: 99%

A Method for Deforming-Driven Exaggerated Facial Animation Generation

Wei

Liu

2008

2008 International Conference on Cyberworlds

View full text Add to dashboard Cite

This paper proposes a method for automatically generating facial animation with exaggerated features from a facial image. According to facial diversity and identity, an exaggerated face can be determined by the neutral face and the exaggeration effect difference that is represented with the deforming parameters. The proposed method utilizes the central point and the feature vector to represent a facial component and then transforms these feature vectors under the control of deforming parameters to generate the exaggerated facial features. The exaggerated facial animation can be driven to generate by the sequence of the deforming parameters. Experimental results prove that the proposed method has the advantages of simplicity, flexibility and directness, and the generated facial animations are expressive.

show abstract

“…Although some literature exists on portrait sketching [3,25] and caricatures [10,24] prior work dedicated to painterly portraits is sparse. DiPaola [9] attempts to map the knowledge domain of the human portrait painter.…”

Section: Related Workmentioning

confidence: 99%

Learnable Stroke Models for Example-based Portrait Painting

Wang

Collomosse

Hunter

et al. 2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We present a novel algorithm for stylizing photographs into portrait paintings comprised of curved brush strokes. Rather than drawing upon a prescribed set of heuristics to place strokes, our system learns a flexible model of artistic style by analyzing training data from a human artist. Given a training pair -a source image and painting of that image -a non-parametric model of style is learned by observing the geometry and tone of brush strokes local to image features. A Markov Random Field (MRF) enforces spatial coherence of style parameters. Style models local to facial features are learned using a semantic segmentation of the input face image, driven by a combination of an Active Shape Model and Graph-cut. We evaluate style transfer between a variety of training and test images, demonstrating a wide gamut of learned brush and shading styles.

show abstract

Facial caricaturing with motion caricaturing in PICASSO system

Cited by 21 publications

References 0 publications

Artistic Rendering of Portraits

Artistic Rendering of Portraits

A Method for Deforming-Driven Exaggerated Facial Animation Generation

Learnable Stroke Models for Example-based Portrait Painting

Contact Info

Product

Resources

About