A trigonal prism-based method for hair image generation

The difficulties involved in modeling and rendering hair in computer graphics are described. An efficient method using a trigonal prism model to render individual human hairs is presented. A wisp model easily controls hair shape with a few parameters. The method also proves effective for rendering eyebrows, eyelashes, beards, moustaches, clothes and personal ornaments such as earrings and hair accessories. A double z-buffer generates the backlighting effect. A simple parabola approximates wisp loci for hair animation. The method makes it possible to draw an enormous number of hairs within a reasonably short time     

The Cluster Hair Model

Modeling and rendering human hair is a very challenging problem in computer graphics. The difficulty comes mainly from the amount of hair to be modeled and the fine shapes of the individual hairs. In this paper, a new cluster hair model is introduced. The new model allows the design and styling of hair to be efficiently performed at the abstract cluster level. The key idea of this work is to embed a volume density model into a generalized cylinder, which is used to specify the envelope shape of a hair cluster, so that the design and manipulation of hair can be globally and efficiently performed. The detail of the hair is then modeled by a volume density model in which a randomly generated density map on the hair base is projected into and deformed along the generalized cylinder. The main advantages of the new model are: (1) it provides a very compact and efficient representation for complex hair styles; (2) it improves significantly the feasibility of and capability for interactive hair modeling and styling; (3) it produces high quality hair images; and (4) it provides a multiresolution model for adaptive rendering. It also has the potential to support efficient dynamic simulation at the cluster level.     

Fur Shading and Modification based on Cone Step Mapping

This paper presents an algorithm for the real time rendering of fur without adding fur‐specific geometry, such as shells, to the object. It is based on Cone Step Mapping and introduces a local distortion of the view vector to simulate a deformation of the heightfield‐bound hair geometry. While this distortion enables a more realistic fur rendering, some limitations emerge and have to be dealt with. A local light reflectance model including approximations of global light interactions with hair and skin is proposed. We furthermore show how material and geometric properties can locally be influenced through standard texture mapping. This includes most notably the local modification of growth and streak direction of the hairs.     

Rendering hair using pixel blending and shadow buffers

A technique is described for adding natural-looking hair to standard rendering algorithms. Using an explicit hair model, in which each individual hair is represented by a three-dimensional curve, the technique uses pixel blending combined with Z-buffer and shadow buffer information from the scene to yield a final anti-aliased image with soft shadows. Although developed for rendering human hair, this technique can also be used to render any model consisting of long filaments of sub-pixel width. The technique can be adapted to any rendering method that outputs Z-buffer and shadow buffer information and is amenable to hardware implementation.     

Real-time animation of complex hairstyles

True real-time animation of complex hairstyles on animated characters is the goal of this work, and the challenge is to build a mechanical model of the hairstyle which is sufficiently fast for real-time performance while preserving the particular behavior of the hair medium and maintaining sufficient versatility for simulating any kind of complex hairstyles. Rather than building a complex mechanical model directly related to the structure of the hair strands, we take advantage of a volume free-form deformation scheme. We detail the construction of an efficient lattice mechanical deformation model which represents the volume behavior of the hair strands. The lattice is deformed as a particle system using state-of-the-art numerical methods, and animates the hairs using quadratic B-spline interpolation. The hairstyle reacts to the body skin through collisions with a metaball-based approximation. The model is highly scalable and allows hairstyles of any complexity to be simulated in any rendering context with the appropriate trade off between accuracy and computation speed, fitting the need of level-of-detail optimization schemes.     

虚拟人物实时毛发动画

提出了一个基于晶格的机械变形方法。晶格被作为一个粒子系统采用数学方法变形，毛发采用2次B样条插值方法绘制。用元球模型处理毛发和身体表面之间碰撞。发型机械模型具有很高的实时性能和通用性，可以用来模拟各种复杂发型。模型可达到各种绘制背景下准确性和计算速度之间的最佳折中。     

Hybrid fur rendering: combining volumetric fur with explicit hair strands

Hair is typically modeled and rendered using either explicitly defined hair strand geometry or a volume texture of hair densities. Taken each on their own, these two hair representations have difficulties in the case of animal fur as it consists of very dense and thin undercoat hairs in combination with coarse guard hairs. Explicit hair strand geometry is not well-suited for the undercoat hairs, while volume textures are not well-suited for the guard hairs. To efficiently model and render both guard hairs and undercoat hairs, we present a hybrid technique that combines rasterization of explicitly defined guard hairs with ray marching of a prismatic shell volume with dynamic resolution. The latter is the key to practical combination of the two techniques, and it also enables a high degree of detail in the undercoat. We demonstrate that our hybrid technique creates a more detailed and soft fur appearance as compared with renderings that only use explicitly defined hair strands. Finally, our rasterization approach is based on order-independent transparency and renders high-quality fur images in seconds.     

Accelerating Hair Rendering by Learning High-Order Scattered Radiance

Efficiently and accurately rendering hair accounting for multiple scattering is a challenging open problem. Path tracing in hair takes long to converge while other techniques are either too approximate while still being computationally expensive or make assumptions about the scene. We present a technique to infer the higher order scattering in hair in constant time within the path tracing framework, while achieving better computational efficiency. Our method makes no assumptions about the scene and provides control over the renderer's bias & speedup. We achieve this by training a small multilayer perceptron (MLP) to learn the higher-order radiance online, while rendering progresses. We describe how to robustly train this network and thoroughly analyze our resulting renderer's characteristics. We evaluate our method on various hairstyles and lighting conditions. We also compare our method against a recent learning based & a traditional real-time hair rendering method and demonstrate better quantitative & qualitative results. Our method achieves a significant improvement in speed with respect to path tracing, achieving a run-time reduction of 40%-70% while only introducing a small amount of bias.     

毛发的结构造型方法

人物的绘制是当今计算机图形学中的一项重要任务,特别吸引人的是头发的生成技术.头发生成技术的难点在于其精细的形状和庞大的数量.文章针对头发提出了弯曲纹元和三维纹理体的概念,并给出了它们的数学表达式以及对不同发型的描述方法.弯曲纹元和三维纹理体是一般三维纹理的结构.带三维纹理的景物是由弯曲纹元和三维纹理体构成的,三维纹理体可再分成多个弯曲纹元,因而指明了三维纹理空间的结构,并解决了三维纹理曲面的造型问题.文章通过不同例子表明了结构造型方法在描述头发中的应用价值.     

Single Photo Estimation of Hair Appearance

Significant progress has been made in high-quality hair rendering, but it remains difficult to choose parameter values that reproduce a given real hair appearance. In particular, for applications such as games where naive users want to create their own avatars, tuning complex parameters is not practical. Our approach analyses a single flash photograph and estimates model parameters that reproduce the visual likeness of the observed hair. The estimated parameters include color absorptions, three reflectance lobe parameters of a multiple-scattering rendering model, and a geometric noise parameter. We use a novel melanin-based model to capture the natural subspace of hair absorption parameters. At its core, the method assumes that images of hair with similar color distributions are also similar in appearance. This allows us to recast the issue as an image retrieval problem where the photo is matched with a dataset of rendered images; we thus also match the model parameters used to generate these images. An earth-mover's distance is used between luminance-weighted color distributions to gauge similarity. We conduct a perceptual experiment to evaluate this metric in the context of hair appearance and demonstrate the method on 64 photographs, showing that it can achieve a visual likeness for a large variety of input photos.     

重建发型的真实感头部建模

提出了从几何模型和多视点彩色图像构造真实感三维头部模型的方法．作为输入数据的彩色图像不仅被用来构造全景纹理图,而且是发型重构的数据源．首先在模型空间定义对应于真实图像平面的虚拟图像平面,恢复不同视点图像中发型外轮廓点的相应三维位置;然后根据发根位置、生长方向和长度,在模型的头皮表面重建发型．另一种发型重构的方法是从多幅图像中抽取的二维发型轮廓线出发,通过立体匹配法恢复其三维位置．然后用Coons-patch法重构发型表面．实验结果显示了文中方法的头部重建效果．     

环境光照下的毛发渲染与外观编辑

提出一种复杂环境光照条件下交互级毛发绘制与外观编辑的算法,其中光源采用球面径向基函数(SRBF)表示.推导出了一个可以用来精确表达Marschner毛发散射函数(Marschner S R,Jensen H W,Cammarano M,et al.Light scattering from human hair fibers.ACM Transactions on Graphics,2003,22(3):780-791)[2]的简洁一维圆高斯表达,该表达可以高效地以解析形式计算每个SRBF光源与毛发散射函数的积分,因此支持高效的单次散射和多次散射计算.与前人工作不同,文中算法完全在运行时进行所有的计算,不需要昂贵的预计算步骤,因此可以动态地改变毛发的散射参数.分析表明,文中提出的近似表示是精确且简洁的.此外,该算法可以处理椭圆头发截面的情况.通过在GPU上实现,文中算法可以达到交互帧率.     

A generative sketch model for human hair analysis and synthesis

In this paper, we present a generative sketch model for human hair analysis and synthesis. We treat hair images as 2D piecewise smooth vector (flow) fields and, thus, our representation is view-based in contrast to the physically-based 3D hair models in graphics. The generative model has three levels. The bottom level is the high-frequency band of the hair image. The middle level is a piecewise smooth vector field for the hair orientation, gradient strength, and growth directions. The top level is an attribute sketch graph for representing the discontinuities in the vector field. A sketch graph typically has a number of sketch curves which are divided into 11 types of directed primitives. Each primitive is a small window (say 5 /spl times/ 7 pixels) where the orientations and growth directions are defined in parametric forms, for example, hair boundaries, occluding lines between hair strands, dividing lines on top of the hair, etc. In addition to the three level representation, we model the shading effects, i.e., the low-frequency band of the hair image, by a linear superposition of some Gaussian image bases and we encode the hair color by a color map. The inference algorithm is divided into two stages: 1) We compute the undirected orientation field and sketch graph from an input image and 2) we compute the hair growth direction for the sketch curves and the orientation field using a Swendsen-Wang cut algorithm. Both steps maximize a joint Bayesian posterior probability. The generative model provides a straightforward way for synthesizing realistic hair images and stylistic drawings (rendering) from a sketch graph and a few Gaussian bases. The latter can be either inferred from a real hair image or input (edited) manually using a simple sketching interface. We test our algorithm on a large data set of hair images with diverse hair styles. Analysis, synthesis, and rendering results are reported in the experiments.     

Modeling Dynamic Hair as a Continuum

In this paper we address the difficult problem of hair dynamics, particularly hair-hair and hair-air interactions. To model these interactions, we propose to consider hair volume as a continuum. Subsequently, we treat the interaction dynamics to be fluid dynamics. This proves to be a strong as well as viable approach for an otherwise very complex phenomenon. However, we retain the individual character of hair, which is vital to visually realistic rendering of hair animation. For that, we develop an elaborate model for stiffness and inertial dynamics of individual hair strand. Being a reduced coordinate formulation, the stiffness dynamics is numerically stable and fast. We then unify the continuum interaction dynamics and the individual hair's stiffness dynamics.     

用弯曲体纹理构造发型

毛发的造型和绘制技术是当今计算机图形学中的一个突出难题.因为头发形状精细、数量庞大,传统的造型和绘制技术很难达到令人满意的效果.针对人的头发,提出并在数学上表示出了弯曲体纹理.接着参照理发师制作发型的过程,将头皮曲面予以特别处理,并以人头部的形状为依据,给出简单发型的构造方法.然后根据头皮曲面上四边形的结构关系,用插值方法将简单造型予以修正和发展,给出了几个发型构造的实例.最后绘制出具有较为真实效果的发型图.     

发带头发模型的快速渲染及发型控制

为了解决虚拟人头发仿真中由于头发数量巨大导致的实时渲染难、发型单一的问题,提出了一种改进的、可实现多种发型的发带头发模型仿真方法。对基于NURBS曲面的头发模型定位控制点时,采用悬梁臂模型表现出头发自然下垂的状态。对传统的Phong光照模型,提出一种快速精确计算反射方向的改进方法,并考虑头发纹理和Phong明暗处理的相互作用。此外,提出一种新颖的发型设计方法,即通过对alpha纹理的控制和对纹理映射施加扰动函数实现不同头发长短和弯曲的造型。实验结果表明,新的方法能快速实现具有高逼真度的虚拟人头发仿真,且支持多种发型。     

HairControl: A Tracking Solution for Directable Hair Simulation

We present a method for adding artistic control to physics‐based hair simulation. Taking as input an animation of a coarse set of guide hairs, we constrain a subsequent higher‐resolution simulation of detail hairs to follow the input motion in a spatially‐averaged sense. The resulting high‐resolution motion adheres to the artistic intent, but is enhanced with detailed deformations and dynamics generated by physics‐based simulation. The technical core of our approach is formed by a set of tracking constraints, requiring the center of mass of a given subset of detail hair to maintain its position relative to a reference point on the corresponding guide hair. As a crucial element of our formulation, we introduce the concept of dynamically‐changing constraint targets that allow reference points to slide along the guide hairs to provide sufficient flexibility for natural deformations. We furthermore propose to regularize the null space of the tracking constraints based on variance minimization, effectively controlling the amount of spread in the hair. We demonstrate the ability of our tracking solver to generate directable yet natural hair motion on a set of targeted experiments and show its application to production‐level animations.     

基于三维规则数据场的快速光线投射法

光线投射法是体绘制技术中的经典算法。该算法原理简单、明了,并能产生高质量的显示图像,但由于所有体素参与了图像绘制,运行速度慢,从而极大制约了其在交互可视化中的运用。论文利用光线穿过三维规则数据场时与某一方向平面簇交点的快速确定及光线投射方向确定后两相邻平面间所截取线段为定长的特点,简化了光线亮度积分公式,从而在图像质量不减低的情况下,快速进行图像绘制。     

人脸定位算法的研究

提出了一种自适应的二级人脸定位算法:HBEL+可变形椭圆模板匹配算法。HBEL算法是针对大多数人都有头发这一特点,以头发定位为基础的人脸定位算法。而对于少数没有头发的人,其人脸都呈现出椭圆轮廓,根据这一特点,在HBEL算法失败后,采用可变形椭圆模板匹配算法对人脸进行定位。     

A GAN-based temporally stable shading model for fast animation of photorealistic hair

Computational Visual Media - We introduce an unsupervised GAN-based model for shading photorealistic hair animations. Our model is much faster than previous rendering algorithms and produces fewer...