Computer Science

We present a nonparametric statistical framework for the quantification, analysis, and propagation of data uncertainty in direct volume rendering (DVR). The state-of-the-art statistical DVR framework allows for preserving the transfer function (TF) of the ground truth function when visualizing uncertain data; however, the existing framework is restricted to parametric models of uncertainty. In this paper, we address the limitations of the existing DVR framework by extending the DVR framework for nonparametric distributions. We exploit the quantile interpolation technique to derive probability distributions representing uncertainty in viewing-ray sample intensities in closed form, which allows for accurate and efficient computation. We evaluate our proposed nonparametric statistical models through qualitative and quantitative comparisons with the mean-field and parametric statistical models, such as uniform and Gaussian, as well as Gaussian mixtures. In addition, we present an extension of the state-of-the-art rendering parametric framework to 2D TFs for improved DVR classifications. We show the applicability of our uncertainty quantification framework to ensemble, downsampled, and bivariate versions of scalar field datasets.

The creation of high-fidelity computer-generated (CG) characters used in film and gaming requires intensive manual labor and a comprehensive set of facial assets to be captured with complex hardware, resulting in high cost and long production cycles. In order to simplify and accelerate this digitization process, we propose a framework for the automatic generation of high-quality dynamic facial assets, including rigs which can be readily deployed for artists to polish. Our framework takes a single scan as input to generate a set of personalized blendshapes, dynamic and physically-based textures, as well as secondary facial components (e.g., teeth and eyeballs). Built upon a facial database consisting of pore-level details, with over 4,000 scans of varying expressions and identities, we adopt a self-supervised neural network to learn personalized blendshapes from a set of template expressions. We also model the joint distribution between identities and expressions, enabling the inference of the full set of personalized blendshapes with dynamic appearances from a single neutral input scan. Our generated personalized face rig assets are seamlessly compatible with cutting-edge industry pipelines for facial animation and rendering. We demonstrate that our framework is robust and effective by inferring on a wide range of novel subjects, and illustrate compelling rendering results while animating faces with generated customized physically-based dynamic textures.

EMU is an efficient and scalable model to simulate bulk musculoskeletal motion with heterogenous materials. First, EMU requires no model reductions, or geometric coarsening, thereby producing results visually accurate when compared to an FEM simulation. Second, EMU is efficient and scales much better than state-of-the-art FEM with the number of elements in the mesh, and is more easily parallelizable. Third, EMU can handle heterogeneously stiff meshes with an arbitrary constitutive model, thus allowing it to simulate soft muscles, stiff tendons and even stiffer bones all within one unified system. These three key characteristics of EMU enable us to efficiently orchestrate muscle activated skeletal movements. We demonstrate the efficacy of our approach via a number of examples with tendons, muscles, bones and joints.

In this paper we propose a fully automatic method for shape correspondence that is widely applicable, and especially effective for non isometric shapes and shapes of different topology. We observe that fully-automatic shape correspondence can be decomposed as a hybrid discrete/continuous optimization problem, and we find the best sparse landmark correspondence, whose sparse-to-dense extension minimizes a local metric distortion. To tackle the combinatorial task of landmark correspondence we use an evolutionary genetic algorithm, where the local distortion of the sparse-to-dense extension is used as the objective function. We design novel geometrically guided genetic operators, which, when combined with our objective, are highly effective for non isometric shape matching. Our method outperforms state of the art methods for automatic shape correspondence both quantitatively and qualitatively on challenging datasets.

Modern rendering libraries provide unprecedented realism, producing real-time photorealistic 3D graphics on commodity hardware. Visual fidelity, however, comes at the cost of increased complexity and difficulty of usage, with many rendering parameters requiring a deep understanding of the pipeline. We propose EasyPBR as an alternative rendering library that strikes a balance between ease-of-use and visual quality. EasyPBR consists of a deferred renderer that implements recent state-of-the-art approaches in physically based rendering. It offers an easy-to-use Python and C++ interface that allows high-quality images to be created in only a few lines of code or directly through a graphical user interface. The user can choose between fully controlling the rendering pipeline or letting EasyPBR automatically infer the best parameters based on the current scene composition. The EasyPBR library can help the community to more easily leverage the power of current GPUs to create realistic images. These can then be used as synthetic data for deep learning or for creating animations for academic purposes.

We present a method to simulate fluid flow on evolving surfaces, e.g., an oil film on a water surface. Given an animated surface (e.g., extracted from a particle-based fluid simulation) in three-dimensional space, we add a second simulation on this base animation. In general, we solve a partial differential equation (PDE) on a level set surface obtained from the animated input surface. The properties of the input surface are transferred to a sparse volume data structure that is then used for the simulation. We introduce one-way coupling strategies from input properties to our simulation and we add conservation of mass and momentum to existing methods that solve a PDE in a narrow-band using the Closest Point Method. In this way, we efficiently compute high-resolution 2D simulations on coarse input surfaces. Our approach helps visual effects creators easily integrate a workflow to simulate material flow on evolving surfaces into their existing production pipeline.

Cloth simulation requires a fast and stable method for interactively and realistically visualizing fabric materials using computer graphics. We propose an efficient cloth simulation method using miniature cloth simulation and upscaling Deep Neural Networks (DNN). The upscaling DNNs generate the target cloth simulation from the results of physically-based simulations of a miniature cloth that has similar physical properties to those of the target cloth. We have verified the utility of the proposed method through experiments, and the results demonstrate that it is possible to generate fast and stable cloth simulations under various conditions.

Sample based ray marching is an effective method for direct volume rendering of unstructured meshes. However, sampling such meshes remains expensive, and strategies to reduce the number of samples taken have received relatively little attention. In this paper, we introduce a method for rendering unstructured meshes using a combination of a coarse spatial acceleration structure and hardware-accelerated ray tracing. Our approach enables efficient empty space skipping and adaptive sampling of unstructured meshes, and outperforms a reference ray marcher by up to 7x.

The spatial anti-aliasing technique for line joins (intersections of the road segments) on vector maps is exclusively crucial to visual experience and system performance. Due to limitations of OpenGL API, one common practice to achieve the anti-aliased effect is splicing multiple triangles at varying scale levels to approximate the fan-shaped line joins. However, this approximation inevitably produces some unreality, and the system rendering performance is not optimal. To circumvent these drawbacks, in this paper, we propose a simple but efficient algorithm which uses only two triangles to substitute the multiple triangles approximation and then renders a realistic fan-shaped curve with alpha operation based on geometrical relation computing. Our experiment shows it has advantages of a realistic anti-aliasing effect, less memory cost, higher frame rate, and drawing line joins without overlapping rendering. Our proposed spatial anti-aliasing technique has been widely used in Internet Maps such as Tencent Mobile Maps and Tencent Automotive Maps.

Conformal mapping, a classical topic in complex analysis and differential geometry, has become a subject of great interest in the area of surface parameterization in recent decades with various applications in science and engineering. However, most of the existing conformal parameterization algorithms only focus on simply-connected surfaces and cannot be directly applied to surfaces with holes. In this work, we propose two novel algorithms for computing the conformal parameterization of multiply-connected surfaces. We first develop an efficient method for conformally parameterizing an open surface with one hole to an annulus on the plane. Based on this method, we then develop an efficient method for conformally parameterizing an open surface with k holes onto a unit disk with k circular holes. The conformality and bijectivity of the mappings are ensured by quasi-conformal theory. Numerical experiments and applications are presented to demonstrate the effectiveness of the proposed methods.