We propose a generalized equation to represent a continuum of surface reconstruction solutions of a given non-integrable gradient field. We show that common approaches such as Poisson solver and Frankot-Chellappa algorithm are special cases of this generalized equation. For a N x N pixel grid, the subspace of all integrable gradient fields is of dimension N 2 - 1. Our framework can be applied to derive a range of meaningful surface reconstructions from this high dimensional space. The key observation is that the range of solutions is related to the degree of anisotropy in applying weights to the gradients in the integration process. While common approaches use isotropic weights, we show that by using a progression of spatially varying anisotropic weights, we can achieve significant improvement in reconstructions. We propose (a) α-surfaces using binary weights, where the parameter a allows trade off between smoothness and robustness, (b) M-estimators and edge preserving regularization using continuous weights and (c) Diffusion using affine transformation of gradients. We provide results on photometric stereo, compare with previous approaches and show that anisotropic treatment discounts noise while recovering salient features in reconstructions.

What Is the Range of Surface Reconstructions from a Gradient Field

Realistic hair modeling is a fundamental part of creating virtual humans in computer graphics. This paper surveys the state of the art in the major topics of hair modeling: hairstyling, hair simulation, and hair rendering. Because of the difficult, often unsolved problems that arise in alt these areas, a broad diversity of approaches is used, each with strengths that make it appropriate for particular applications. We discuss each of these major topics in turn, presenting the unique challenges facing each area and describing solutions that have been presented over the years to handle these complex issues. Finally, we outline some of the remaining computational challenges in hair modeling

/pdf/a-survey-on-hair-modeling-styling-simulation-and-rendering-1sdf5kj627.pdf

A Survey on Hair Modeling: Styling, Simulation, and Rendering

While total variation is among the most popular regularizers for variational problems, its extension to functions with values in a manifold is an open problem. In this paper, we propose the first algorithm to solve such problems which applies to arbitrary Riemannian manifolds. The key idea is to reformulate the variational problem as a multilabel optimization problem with an infinite number of labels. This leads to a hard optimization problem which can be approximately solved using convex relaxation techniques. The framework can be easily adapted to different manifolds including spheres and three-dimensional rotations, and allows to obtain accurate solutions even with a relatively coarse discretization. With numerous examples we demonstrate that the proposed framework can be applied to variational models that incorporate chromaticity values, normal fields, or camera trajectories.

/pdf/total-variation-regularization-for-functions-with-values-in-4yjzp3vbxt.pdf

Total Variation Regularization for Functions with Values in a Manifold

Dynamic hair strands have complex structures and experience intricate collisions and occlusion, posing significant challenges for high-quality reconstruction of their motions. We present a comprehensive dynamic hair capture system for reconstructing realistic hair motions from multiple synchronized video sequences. To recover hair strands' temporal correspondence, we propose a motion-path analysis algorithm that can robustly track local hair motions in input videos. To ensure the spatial and temporal coherence of the dynamic capture, we formulate the global hair reconstruction as a spacetime optimization problem solved iteratively. Demonstrated using a range of real-world hairstyles driven by different wind conditions and head motions, our approach is able to reconstruct complex hair dynamics matching closely with video recordings both in terms of geometry and motion details.

/pdf/dynamic-hair-capture-using-spacetime-optimization-1raol04w2r.pdf

Dynamic hair capture using spacetime optimization

多角形的模型是 3D 目标的受欢迎的代表。在计算应用的多角形的模型的使用经常要求一个模型到适当地绑 3D 固体。也就是说，多角形的模型需要被闭上，歧管，并且没有自我交叉。这篇论文为修理不满足的模型调查可观的文学这标准，集中于由他们的方法论和能力分类他们。我们希望把指针提供给进一步的读物因为研究人员和专业人员，和为未来的有希望的方向的建议研究努力。这篇文章(doi:10.1007/s11390-009-9206-7 ) 的联机版本包含增补材料，它对授权的用户可得到。

Fixing Geometric Errors on Polygonal Models： A Survey

We construct novel car designing tool, which helps car designers to design cars efficiently and stimulates their artistic sensibilities. Cars are synthesized by analyzing various existing car body shapes and extracting meaningful attributes that represent the features of these shapes. First, a database of existing cars is created. We analyze all shapes using principal component analysis (PCA), then, gain attributes that indicate the typical features of those car shapes. By manipulating the weight of each attribute in the PCA space, we can create car shapes. Second, by analyzing the features of specific car groups, i.e. manufacturer, genre, era, etc, we discover attributes that discriminate between these groups. We can generate a new type of cars by adding these features onto any existing car i.e. a BMW-like Mercedes. .

Car designing tool using multivariate analysis

Creating natural looking hair motion is considered to be one of the most difficult and time consuming challenges in CG animation. A detailed physics-based model is essential in creating convincing hair animation. However, hair animation created using detailed hair dynamics might not always be the result desired by creators. For this reason, a hair simulation system that is both detailed and editable is required in contemporary Computer Graphics. In this paper we therefore, propose the use of External Force Field (EFF) to construct hair motion using a motion capture system. Furthermore, we have developed a system for editing the hair motion obtained using this process. First, the environment around a subject is captured using a motion capture system and the EFF is defined. Second, we apply our EFF-based hair motion editing system to produce creator-oriented hair animation. Consequently, our editing system enables creators to develop desired hair animation intuitively without physical discontinuity.

Directable and stylized hair simulation

An Interactive Tool for Editing Shadows in Cartoon Animation

The present invention relates to a method for reconstructing a three-dimensional surface in a domain wherein the three-dimensional surface is reconstructed from a two- dimensional sketch comprising at least one stroke with a vector field assigned to the at least one stroke. The method comprises the steps of: interpolating the vector field to form a dense vector field; and reconstructing the surface using the dense vector field; wherein interpolating the vector field comprises minimizing a non-linear functional of the vector field with a curl-free constraint on the dense vector field, the non-linear functional of the vector field involving terms defined over the domain and a term defined over the at least one stroke, and wherein the non-linear functional of the vector field is minimized using an augmented Lagrangian method.

A method for reconstructing a 3d surface from a 2d sketch

The reality in human motions is often dominant for success of animation recently. Commercial mocap systems prevail to obtain human motion from actual motions. On the basis of the data obtained by a mocap system, a skeletal structure model is needed to construct a CG character. As a method of creating a skeletal structure model, there is always a locating rule to put markers to right place on the subject’s skin, which is often recommended by a mocap system vender. However, the rule cannot be applied every subject person easily. This is the reason why it is difficult to find subject-specific joint positions. In this research, therefore, observing inside of human body with a help of Magnetic Resonance Imaging (MRI), our final goal is to construct an accurate and detailed bone structure model in order to make more realistic animation.

Eiji Sugisaki

Papers

Car designing tool using multivariate analysis

Directable and stylized hair simulation

An Interactive Tool for Editing Shadows in Cartoon Animation

A method for reconstructing a 3d surface from a 2d sketch

Reconstructing motion using a human structure model