Learning shape and texture progression for young child face aging

Face aging (FA) for young faces refers to rendering the aging faces at target age for an individual, generally under 20s, which is an important topic of facial age analysis. Unlike traditional FA for adults, it is challenging to age children with one deep learning-based FA network, since there are deformations of facial shapes and variations of textural details. To alleviate the deficiency, a unified FA framework for young faces is proposed, which consists of two decoupled networks to apply aging image translation. It explicitly models transformations of geometry and appearance using two components: GD-GAN, which simulates the Geometric Deformation using Generative Adversarial Network; TV-GAN, which simulates the Textural Variations guided by the age-related saliency map. Extensive experiments demonstrate that our method has advantages over the state-of-the-art methods in terms of synthesizing visually plausible images for young faces, as well as preserving the personalized features.     

几何造型的自由畸变方法

几何造型是计算机图形学的重要研究内容，ＣＡＤ／ＣＡＭ的核心技术，现行的许多造型系统仅限于造型二次曲面及旋转曲面，没有自由曲面造型能力，本文研究的自由畸变为法，很容易扩展这些系统的自由曲面造型功能，该方法已成功地用于扩展ＭＯＶＩＥ．ＢＹＵ系统的自由曲面造型功能。     

An introduction to Wu's method for mechanical theorem proving in geometry

Wu's algebraic method for mechanically proving geometry theorems is presented at a level as elementary as possible with sufficient examples for further understanding the complete method.The work reported here was supported by NSF Grant DCR-8503498.     

Applications of the 4×4 determinant method and the POLYGON ENGINE

In the first half of the paper, various types of processing pertaining to a polygon, using the 4×4 determinant theories are explained along with a new containment test algorithm of a point in a polygon. In the latter half of the paper, a general-purpose geometric processor, the POLYGON ENGINE, is presented which can deal with various types of interference problems, such as Boolean operations in solid modelling, hidden line and surface eliminations, ray tracing and so on. It is, a successor of the TRIANGLE PROCESSOR and is also based upon the 4×4 determinant theories [4–6]. While the TRIANGLE PROCESSOR processes a triangulated polygon on a triangle-by-triangle basis, the POLYGON ENGINE can treat a polygon without triangulation. The latter is expected to be more functional, more efficient and easier to use.     

Treatment of Natural Geometry in Finite Volume River Flow Computations

A method is proposed for the treatment of irregular bathymetry in one-dimensional finite volume computations of open-channel flow. The strategy adopted is based on a reformulation of the Saint-Venant equations. In contrast with the usual treatment of topography effects as source terms, the method accounts for slope and nonprismaticity by modifying the momentum flux. This makes it possible to precisely balance the hydrostatic pressure contributions associated with variations in valley geometry. The characteristic method is applied to the revised equations, yielding topographic corrections to the numerical fluxes of an upwind scheme. Further adaptations endow the scheme with an ability to capture transcritical sections and wetting fronts in channels of abrupt topography. To test the approach, the scheme is first applied to idealized benchmark problems. The method is then used to route a severe flood through a complex river system: the Tanshui in Northern Taiwan. Computational results compare favorably with gauge records. Discrepancies in water stage represent no more than a fraction of the magnitude of typical bathymetry variations.     

On the algebraic formulation of certain geometry statements and mechanical geometry theorem proving

In this paper we analyze the algebraic formulations of certain geometry statements appearing in recent literature related to mechanical geometry theorem proving and give several examples to show that one of these formulations can cause serious problems. We clarify a formulation which is essentially due to W. T. Wu and, in our opinion, is the most satisfactory.This author was supported by NSF Grants DCR-8503498 and CCR-8702108.     

Target differentiation with simple infrared sensors using statistical pattern recognition techniques

This study compares the performances of various statistical pattern recognition techniques for the differentiation of commonly encountered features in indoor environments, possibly with different surface properties, using simple infrared (IR) sensors. The intensity measurements obtained from such sensors are highly dependent on the location, geometry, and surface properties of the reflecting feature in a way that cannot be represented by a simple analytical relationship, therefore complicating the differentiation process. We construct feature vectors based on the parameters of angular IR intensity scans from different targets to determine their geometry and/or surface type. Mixture of normals classifier with three components correctly differentiates three types of geometries with different surface properties, resulting in the best performance (100%) in geometry differentiation. Parametric differentiation correctly identifies six different surface types of the same planar geometry, resulting in the best surface differentiation rate (100%). However, this rate is not maintained with the inclusion of more surfaces. The results indicate that the geometrical properties of the targets are more distinctive than their surface properties, and surface recognition is the limiting factor in differentiation. The results demonstrate that simple IR sensors, when coupled with appropriate processing and recognition techniques, can be used to extract substantially more information than such devices are commonly employed for.     

A Generic Pigment Model for Digital Painting

We propose a generic pigment model suitable for digital painting in a wide range of genres including traditional Chinese painting and water-based painting. The model embodies a simulation of the pigment-water solution and its interaction with the brush and the paper at the level of pigment particles; such a level of detail is needed for achieving highly intricate effects by the artist. The simulation covers pigment diffusion and sorption processes at the paper surface, and aspects of pigment particle deposition on the paper. We follow rules and formulations from quantitative studies of adsorption and diffusion processes in surface chemistry and the textile industry. The result is a pigment model that spans a continuum from the very wet to the very dry brush stroke effects. We also propose a new pigment mixing method based on machine learning techniques to emulate pigment mixing in real life as well as to support the creation of new artificial pigments. To experiment with the proposed model, we embedded the model in a sophisticated digital brush system. The combined system exhibits interactive speed on a modest PC platform. http://www.cs.hku.hk/~songhua/pigment provides supplementary materials for this paper.     

几何仿真在数控车削加工过程中的应用

叙述了数控加工中NC代码的传统验证方法及几何仿真的目的和意义，着重讨论了数控车床几何仿真的系统结构以及NC代码验证程序的流程，最后分析了几何仿真中欠切与过切的布尔差算法。通过几何仿真，可以预见机械加工中的许多问题，从而降低设计与制造的成本，提高加工效率。