SIGGRAPH 2019 Papers

Chinese glove puppetry is a traditional art with a long history and widely spread in the folk ever. This paper presents a collaborative work in multi-user virtual reality system for puppetry's opera. According to our developed system, each user has a unique perspective on any shared virtual world and interaction through our virtual reality network. This system achieves human-computer interaction and realizes the interaction between people. In addition, it brings an entertaining experience to users and easy to operate for all ages. In order to cultural preservation, we can record a grandmaster's puppet show performance in our system. Our research not only delivers a balance of art and technology in culture creativity, but also preserve folk art.

Commercially available full-color 3D printing allows for detailed control of material deposition in a volume, but an exact reproduction of a target surface appearance is hampered by the strong subsurface scattering that causes nontrivial volumetric cross-talk at the print surface. Previous work showed how an iterative optimization scheme based on accumulating absorptive materials at the surface can be used to find a volumetric distribution of print materials that closely approximates a given target appearance. In this work, we first revisit the assumption that pushing the absorptive materials to the surface results in minimal volumetric cross-talk. We design a full-fledged optimization on a small domain for this task and confirm this previously reported heuristic. Then, we extend the above approach that is critically limited to color reproduction on planar surfaces, to arbitrary 3D shapes. Our method enables high-fidelity color texture reproduction on 3D prints by effectively compensating for internal light scattering within arbitrarily shaped objects. In addition, we propose a content-aware gamut mapping that significantly improves color reproduction for the pathological case of thin geometric features. Using a wide range of sample objects with complex textures and geometries, we demonstrate color reproduction whose fidelity is superior to state-of-the-art drivers for color 3D printers.

Probabilistic distribution models like Gaussian mixtures have shown great potential for improving both the quality and speed of several geometric operators. This is largely due to their ability to model large fuzzy data using only a reduced set of atomic distributions, allowing for large compression rates at minimal information loss. We introduce a new surface model that utilizes these qualities of Gaussian mixtures for the definition and control of a parametric smooth surface. Our approach is based on an enriched mesh data structure, which describes the probability distribution of spatial surface locations around each vertex via a Gaussian covariance matrix. By incorporating this additional covariance information, we show how to define a smooth surface via a nonlinear probabilistic subdivision operator based on products of Gaussians, which is able to capture rich details at fixed control mesh resolution. This entails new applications in surface reconstruction, modeling, and geometric compression.

We present a generative neural network that enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently. Our key observation is that indoor scene structures are inherently hierarchical. Hence, our network is not convolutional; it is a recursive neural network, or RvNN. Using a dataset of annotated scene hierarchies, we train a variational recursive autoencoder, or RvNN-VAE, which performs scene object grouping during its encoding phase and scene generation during decoding. Specifically, a set of encoders are recursively applied to group 3D objects based on support, surround, and co-occurrence relations in a scene, encoding information about objects’ spatial properties, semantics, and relative positioning with respect to other objects in the hierarchy. By training a variational autoencoder (VAE), the resulting fixed-length codes roughly follow a Gaussian distribution. A novel 3D scene can be generated hierarchically by the decoder from a randomly sampled code from the learned distribution. We coin our method GRAINS, for Generative Recursive Autoencoders for INdoor Scenes. We demonstrate the capability of GRAINS to generate plausible and diverse 3D indoor scenes and compare with existing methods for 3D scene synthesis. We show applications of GRAINS including 3D scene modeling from 2D layouts, scene editing, and semantic scene segmentation via PointNet whose performance is boosted by the large quantity and variety of 3D scenes generated by our method.

Due to the increased availability and accuracy of GPS sensors, the field of movement ecology has been able to benefit from larger datasets of movement data. As miniaturisation and the efficiency of electronic components have improved, additional sensors have been coupled with GPS tracking to enable features related to the animal's state at a given position to be recorded. This capability is especially relevant to understand how environmental conditions may affect movement.

This paper investigates the use of fundamental solutions for animating detailed linear water surface waves. We first propose an analytical solution for efficiently animating circular ripples in closed form. We then show how to adapt the method of fundamental solutions (MFS) to create ambient waves interacting with complex obstacles. Subsequently, we present a novel wavelet-based discretization which outperforms the state of the art MFS approach for simulating time-varying water surface waves with moving obstacles. Our results feature high-resolution spatial details, interactions with complex boundaries, and large open ocean domains. Our method compares favorably with previous work as well as known analytical solutions. We also present comparisons between our method and real world examples.

In this article, we present a novel representation for deformation fields of 3D shapes, by considering the induced changes in the underlying metric. In particular, our approach allows one to represent a deformation field in a coordinate-free way as a linear operator acting on real-valued functions defined on the shape. Such a representation provides both a way to relate deformation fields to other classical functional operators and enables analysis and processing of deformation fields using standard linear-algebraic tools. This opens the door to a wide variety of applications such as explicitly adding extrinsic information into the computation of functional maps, intrinsic shape symmetrization, joint deformation design through precise control of metric distortion, and coordinate-free deformation transfer without requiring pointwise correspondences. Our method is applicable to both surface and volumetric shape representations and we guarantee the equivalence between the operator-based and standard deformation field representation under mild genericity conditions in the discrete setting. We demonstrate the utility of our approach by comparing it with existing techniques and show how our representation provides a powerful toolbox for a wide variety of challenging problems.

In this paper, we propose a method to colorize line drawings of anime characters' faces with colors from a reference image. Previous studies using reference images often fail to realize fully-automatic colorization, especially for small areas, e.g., eye colors in the resulting image may differ from the reference image. The proposed method accurately colorizes eyes in the input line drawing using automatically computed hints. The hints are round patches used to specify the positions and corresponding colors extracted from the eye areas of a reference image.

Transmission of radiation through spatially-correlated media has demonstrated deviations from the classical exponential law of the corresponding uncorrelated media. In this paper, we propose a general, physically-based method for modeling such correlated media with non-exponential decay of transmittance. We describe spatial correlations by introducing the Fractional Gaussian Field (FGF), a powerful mathematical tool that has proven useful in many areas but remains under-explored in graphics. With the FGF, we study the effects of correlations in a unified manner, by modeling both high-frequency, noise-like fluctuations and k-th order fractional Brownian motion (fBm) with a stochastic continuity property. As a result, we are able to reproduce a wide variety of appearances stemming from different types of spatial correlations. Compared to previous work, our method is the first that addresses both short-range and long-range correlations using physically-based fluctuation models. We show that our method can simulate different extents of randomness in spatially-correlated media, resulting in a smooth transition in a range of appearances from exponential falloff to complete transparency. We further demonstrate how our method can be integrated into an energy-conserving RTE framework with a well-designed importance sampling scheme and validate its ability compared to the classical transport theory and previous work.

We propose a potential fluid-measurement technology aimed at supporting biomechanics research of water sports using fluid simulation and motion analysis. Cellulose nanofibers introduced into the water as tracer particles to visualize the movement of water. An optical property of nanofibers, called flow birefringence, makes water flows brighter than their surroundings when placed between right and left circularly polarized plates. We tested the capability of the technology in a water tank and succeeded in using an existing particle-tracking method-particle image velocimetry (PIV)-to measure the flows from a pump in the tank.

Natural disasters constitute unexpected and severe threats with devastating effects on communities worldwide. Recent studies emphasize the importance of public awareness and training of first responders in disaster preparedness and response activities. This paper presents a virtual reality framework that creates a realistic 3D gaming environment with real-time and historical weather and disaster conditions. Main goals of the project are to increase public awareness about disasters by using gamification techniques, and train and evaluate emergency responders by simulating real-life scenarios. The system is supported by voice recognition to interact with the virtual world, and analyze user's actions and voice to detect emotional and psychological state.

This paper tackles the challenging problem of constrained hexahedral meshing. An algorithm is introduced to build combinatorial hexahedral meshes whose boundary facets exactly match a given quadrangulation of the topological sphere. This algorithm is the first practical solution to the problem. It is able to compute small hexahedral meshes of quadrangulations for which the previously known best solutions could only be built by hand or contained thousands of hexahedra. These challenging quadrangulations include the boundaries of transition templates that are critical for the success of general hexahedral meshing algorithms. The algorithm proposed in this paper is dedicated to building combinatorial hexahedral meshes of small quadrangulations and ignores the geometrical problem. The key idea of the method is to exploit the equivalence between quad flips in the boundary and the insertion of hexahedra glued to this boundary. The tree of all sequences of flipping operations is explored, searching for a path that transforms the input quadrangulation Q into a new quadrangulation for which a hexahedral mesh is known. When a small hexahedral mesh exists, a sequence transforming Q into the boundary of a cube is found; otherwise, a set of pre-computed hexahedral meshes is used. A novel approach to deal with the large number of problem symmetries is proposed. Combined with an efficient backtracking search, it allows small shellable hexahedral meshes to be found for all even quadrangulations with up to 20 quadrangles. All 54, 943 such quadrangulations were meshed using no more than 72 hexahedra. This algorithm is also used to find a construction to fill arbitrary domains, thereby proving that any ball-shaped domain bounded by n quadrangles can be meshed with no more than 78 n hexahedra. This very significantly lowers the previous upper bound of 5396 n.

We propose a novel and intuitive method for exploring recoloring variations of vector graphics. Compared with existing methods, ours is specifically tailored for vector graphics, where color distributions are sparser and are explicitly stored using constructs like solid colors or gradients, independent from other semantical and spatial relationships. Our method tries to infer some of them before formulating color transfer as a transport problem between the weighted color distributions of the reference and the target vector graphics. We enable creative exploration by providing fine-grain control over the resulting transfer, allowing users to modify relative color distributions in real-time.

Future auto-stereoscopic displays offer us an amazing possibility of virtual reality without the need for head mounted displays. Since fundamentally though we only need to generate viewpoints for known observers, the classical approach to render all views at once is wasteful in terms of GPU resources and limits the scale of an auto-stereoscopic display. We present a technique that reduces GPU consumption when using an auto-stereoscopic displays by giving the display a context awareness of its observers. The technique was first applied to the Looking Glass device on the Unity3D platform. Rather than rendering 45 different views at the same time, for each observer, the framework only requires six views that are visible to both eyes based on the tracked eye positions. Given the current specifications of this device, the framework helps save 73% GPU consumption for Looking Glass if it was to render a 8K X 8K resolution scene, and the saved GPU consumption increases as the resolution increases. This technique can be applied to reduce future GPU requirements for auto-stereoscopic displays in the future.

Modern medical science strongly depends on imaging technologies for accurate diagnose and treatment planning. Raw medical images generally require post-processing - like edge and contrast enhancement, and noise removal - for visualization. In this paper, a clustering-based contrast enhancement technique is presented for computed tomography (CT) images.

During the last decade, we have been witnessing the continued development of new time-of-flight imaging devices, and their increased use in numerous and varied applications. However, physics-based rendering techniques that can accurately simulate these devices are still lacking: while existing algorithms are adequate for certain tasks, such as simulating transient cameras, they are very inefficient for simulating time-gated cameras because of the large number of wasted path samples. We take steps towards addressing these deficiencies, by introducing a procedure for efficiently sampling paths with a predetermined length, and incorporating it within rendering frameworks tailored towards simulating time-gated imaging. We use our open-source implementation of the above to empirically demonstrate improved rendering performance in a variety of applications, including simulating proximity sensors, imaging through occlusions, depth-selective cameras, transient imaging in dynamic scenes, and non-line-of-sight imaging.

In this paper, we introduce BiMocq2, an unconditionally stable, pure Eulerianbased advection scheme to efficiently preserve the advection accuracy of all physical quantities for long-term fluid simulations. Our approach is built upon the method of characteristic mapping (MCM). Instead of the costly evaluation of the temporal characteristic integral, we evolve the mapping function itself by solving an advection equation for the mappings. Dual mesh characteristics (DMC) method is adopted to more accurately update the mapping. Furthermore, to avoid visual artifacts like instant blur and temporal inconsistency introduced by re-initialization, we introduce multi-level mapping and back and forth error compensation. We conduct comprehensive 2D and 3D benchmark experiments to compare against alternative advection schemes. In particular, for the vortical flow and level set experiments, our method outperforms almost all state-of-art hybrid schemes, including FLIP, PolyPic and Particle-Level-Set, at the cost of only two Semi-Lagrangian advections. Additionally, our method does not rely on the particle-grid transfer operations, leading to a highly parallelizable pipeline. As a result, more than 45× performance acceleration can be achieved via even a straightforward porting of the code from CPU to GPU.

Simulating (elastically) deformable models that can collide with each other and with the environment remains a challenging task. The resulting contact problems can be elegantly approached using Lagrange multipliers to represent the unknown magnitude of the response forces. Typical methods construct and solve a Linear Complementarity Problem (LCP) to obtain the response forces. This requires the inverse of the generalized mass matrix, which is generally hard to obtain for deformable-body problems. In this article, we tackle such contact problems by directly solving the Mixed Linear Complementarity Problem (MLCP) and omitting the construction of an LCP matrix. Since a convex quadratic program with linear constraints is equivalent to an MLCP, we propose to use a Conjugate Residual (CR) solver as the backbone of our collision response system. By dynamically updating the set of active constraints, the MLCP with inequality constraints can be solved efficiently. We also propose a simple yet efficient preconditioner that ensures faster convergence. Finally, our approach is faster than existing methods (at the same accuracy), and it allows accurate treatment of friction.