Golam Ashraf

Shape stylized face caricatures

Facial caricatures exaggerate key features to emphasize unique structural and personality traits. It is quite a challenge to retain the identity of the original person despite the exaggerations. We find that primitive shapes are well known for representing certain personality traits, in art and psychology literature. Unfortunately, current automated caricature generation techniques ignore the role of primitive shapes in stylization. These methods are limited to emphasizing key distances from a fixed Golden Ratio, or computing the best mapping in a proprietary example set of (real-image, cartoon portrait) pairs. We propose a novel stylization algorithm that allows expressive vector control with primitive shapes. We propose three shape-inspired ideas for caricature generation from input frontal face portraits: 1) Extrapolation in the Golden Ratio and Primitive Shape Spaces; 2) Use of art and psychology stereotype rules; 3) Constrained adaptation to a supplied cartoon mask. We adopt a recent mesh-less parametric image warp algorithm for the hair, face and facial features (eyes, mouth, eyebrows, nose, and ears) that provides fast results. The user can synthesize a range of caricatures by changing the number of identity constraints, relaxing shape change constraints, and controlling a global exaggeration scaling factor. Different cartoon templates and art rules can make the persons caricature mimic different personalities, and yet retain basic identity. The proposed method is easy to use and implement, and can be extended to create animated facial caricatures for games, film and interactive media applications.

Learning from humanoid cartoon designs

Character design is a key ingredient to the success of any comic-book, graphic novel, or animated feature. Artists typically use shape, size and proportion as the first design layer to express role, physicality and personality traits. In this paper, we propose a knowledge mining framework that extracts primitive shape features from finished art, and trains models with labeled metadata attributes. The applications are in shape-based query of character databases as well as label-based generation of basic shape scaffolds, providing an informed starting point for sketching new characters. It paves the way for more intelligent shape indexing of arbitrary well-structured objects in image libraries. Furthermore, it provides an excellent tool for novices and junior artists to learn from the experts. We first describe a novel primitive based shape signature for annotating character body-parts. We then use support vector machine to classify these characters using their body parts shape signature as features. The proposed data transformation is computationally light and yields compact storage. We compare the learning performance of our shape representation with a low-level point feature representation, with substantial improvement.

Hardware accelerated skin deformation for animated crowds

Real time rendering of animated crowds has many practical multimedia applications. The Graphics Processor Unit (GPU) is being increasingly employed to accelerate associated rendering and deformation calculations. This paper explores skeletal deformation calculations on the GPU for crowds of articulated figures. It compares a few strategies for efficient reuse of such calculations on clones. We further propose ideas that will reduce chances of detecting such duplication. The system has been implemented for modern PCs with Graphics Accelerator cards that support GPU Shader Model 3.0, and come with accelerated bi-directional PCI express bus communication. We have achieved a realistic crowd population of 1000 animated humans at interactive rates.

Mining Human Shape Perception with Role Playing Games

‘Games with a purpose’ is a paradigm where games are designed to computationally capture the essence of the underlying collective human conscience or commonsense that plays a major role in decision-making. This human computing method ensures spontaneous participation of players who, as a byproduct of playing, provide useful data that is impossible to generate computationally and extremely difficult to collect through extensive surveys. In this paper we describe a game that allows us to collect data on human perception of character body shapes. The paper describes the experimental setup, related game design constraints, art creation, and data analysis. In our interactive roleplaying detective game titled Villain Ville, players are asked to characterize different versions of full-body color portraits of three villain characters. They are later supposed to correctly match their character-trait ratings to a set of characters represented only with outlines of primitive vector shapes. By transferring human intelligence tasks into core game-play mechanics, we have successfully managed to collect motivated data. Preliminary analysis on game data generated by 50 secondary school students shows a convergence to some common perception associations between role, physicality and personality. We hope to harness this game to discover perception for a wide variety of body-shapes to build up an intelligent shape-trait-role model, with application in tutored drawing, procedural character geometry creation and intelligent retrieval.

Learning Character Design from Experts and Laymen

The use of pose and proportion to represent character traits is well established in art and psychology literature. However, there are no Golden Rules that quantify a generic design template for stylized character figure drawing. Given the wide variety of drawing styles and a large feature dimension space, it is a significant challenge to extract this information automatically from existing cartoon art. This paper outlines a game-inspired methodology for systematically collecting layman perception feedback, given a set of carefully chosen trait labels and character silhouette images. The rated labels were clustered and then mapped to the pose and proportion parameters of characters in the dataset. The trained model can be used to classify new drawings, providing valuable insight to artists who want to experiment with different poses and proportions in the draft stage. The proposed methodology was implemented as follows: 1) Over 200 full-body, front-facing character images were manually annotated to calculate pose and proportion, 2) A simplified silhouette was generated from the annotations to avoid copyright infringements and prevent users from identifying the source of our experimental figures, 3) An online casual role-playing puzzle game was developed to let players choose meaningful tags (role, physicality and personality) for characters, where tags and silhouettes received equitable exposure, 4) Analysis on the generated data was done both in stereotype label space as well as character shape space, 5) Label filtering and clustering enabled dimension reduction of the large description space, and subsequently, a select set of design features were mapped to these clusters to train a neural network classifier. The mapping between the collected perception and shape data give us quantitative and qualitative insight into character design. It opens up applications for creative reuse of (and deviation from) existing character designs.

Sketch based 3D character deformation

Most 3D character editing tools are complex and non-intuitive. It takes lot of skill and labor from the artists to create even a draft 3D humanoid model. This paper proposes an intuitive 2D sketch-driven drafting tool that allows users to quickly shape and proportion existing detailed 3D models. We leverage on our existing vector shape representation to describe character bodypart segments as affine-transformed circle-triangle-square shape blends. This is done for both the input 2D doodle as well as for the extracted point clouds from 3D library mesh. The simplified body part vector shapes help describe the relative deformation between the source (3D library mesh) and the target (2D frontal sketch). The actual deformation is done using automatically setup Free Form Deformation cages. To perform body-part shape analysis, we first segment the mesh with Baran and Popovics algorithm for automatic fitting of an input skeleton to a given 3D mesh, followed by our existing 2D shape vector fitting process. There are several promising character design applications of this paper; e.g. accelerated personality pre-visualization in movie production houses, intuitive customization of avatars in games and interactive media, and procedural character generation.