Junghyun Cho

3D Modeling from Photos Given Topological Information

Reconstructing 3D models given a single-view 2D information is inherently an ill-posed problem and requires additional information such as shape prior or user input.We introduce a method to generate multiple 3D models of a particular category given corresponding photographs when the topological information is known. While there is a wide range of shapes for an object of a particular category, the basic topology usually remains constant.In consequence, the topological prior needs to be provided only once for each category and can be easily acquired by consulting an existing database of 3D models or by user input. The input of topological description is only connectivity information between parts; this is in contrast to previous approaches that have required users to interactively mark individual parts. Given the silhouette of an object and the topology, our system automatically finds a skeleton and generates a textured 3D model by jointly fitting multiple parts. The proposed method, therefore, opens the possibility of generating a large number of 3D models by consulting a massive number of photographs. We demonstrate examples of the topological prior and reconstructed 3D models using photos.

A Novel Framework for Assessing Facial Attractiveness Based on Facial Proportions

In this paper, we present a novel framework for automatically assessing facial attractiveness that considers four ratio feature sets as objective elements of facial attractiveness. In our framework, these feature sets are combined with three regression-based predictors to estimate a facial beauty score. To enhance the system’s performance to make it comparable with human scoring, we apply a score fusion technique. Experimental results show that the attractiveness score obtained by the proposed framework better correlates with human assessments than the scores from other predictors. The framework’s modularity allows any features or predictors to be integrated into the facial attractiveness measure. Our proposed framework can be applied to many beauty-related fields, such as the plastic surgery, cosmetics, and entertainment industries.

3-Dimensional Face from a Single Face Image with Various Expressions

Generating a user-specific 3D face model is useful for a variety of applications, such as facial animation, games or movie industries. Recently, there have been spectacular developments in 3D sensors, however, accurately recovering the 3D shape model from a single image is a major challenge of computer vision and graphics. In this paper, we present a method that can not only acquire a 3D shape from only a single face image but also reconstruct facial expression. To accomplish this, a 3D face database with a variety of identities and facial expressions was restructured as a data array which was decomposed for the acquisition of bilinear models. With this model, we represent facial variances as two kinds of elements: expressions and identities. Then, target face image is fitted to 3D model while estimating its expression and shape parameters. As application example, we transferred expressions to reconstructed 3D models and naturally applied new facial expressions to show the efficiency of the proposed method.

Reduced illumination patterns for acquisition of specular and diffuse normal maps

We propose an efficient computational method to acquire diffuse and specular normal map with three types of illumination patterns by removing the redundancy of the conventional method. By analyzing the relationship between four reflectances under XY Z-gradient and constant patterns, the number of patterns needed is reduced to three patterns.

Parameterized Facial Modelling and Animation

Facial modelling is a fundamental technique in a variety of applications in computer graphics, computer vision and pattern recognition areas. As 3D technologies evolved over the years, the quality of facial modelling greatly improved. To enhance the modelling quality and controllability of the model further, parametric methods, which represent or manipulate facial attributes (e.g. identity, expression, viseme) with a set of control parameters, have been proposed in recent years. The aim of this chapter is to give a comprehensive overview of current state-of-the-art parametric methods for realistic facial modelling and animation.

3D Face-Aware Electronics with Low-Resolution Imaging

What if your electronics with cheap cameras can reveal 3D faces of captured people? In daily life, we use a lot of consumer electronics employing cameras such as a mobile phone, a tablet PC, a CCTV, a car black box, and so on. If such devices provide 3D facial shapes of 2-dimensionally framed people, it would benefit new applications and services in higher dimensional imaging, security, HCI Human-Computer Interaction, AR Augmented Reality, and mobile applications like phone games. This paper introduces a novel method to realize the functionality in computational electronics with low-resolution imaging.

Expression Recognition Driven Virtual Human Animation

Since the character expressions are high dimensional, it is not easy to control them intuitively with simple interface. So far, existing controlling and animating methods are mainly based on three dimensional motion capture system for high quality animation. However, using the three dimensional motion capture system is not only unhandy but also quite expensive. In this paper, we therefore present a new control method for 3D facial animation based on expression recognition technique. We simply utilize off-the-shelf a single webcam as a control interface which can easily combine with blendshape technique for 3D animation. We measure the user’s emotional state by a robust facial feature tracker and facial expression classifier and then transfer the measured probabilities of facial expressions to the domain of blendshape basis. We demonstrate our method can be one of efficient interface for virtual human animation through our experiments.