SIGGRAPH 2020 Papers

Volumetric PolyCube-Map-based methods offer automatic ways to construct all-hexahedral meshes for closed 3D polyhedral domains, but their meshing quality is limited by the lack of interior singularities and feature alignment. In the presented work, we propose cut-enhanced PolyCube-Maps, to introduce essential interior singularities and preserve most input features. Our main idea is simple and intuitive: by inserting proper parameterization seams into the initial PolyCube-Map via novel PolyCube cutting operations, the mapping distortion can be reduced significantly. The cut-enhanced PolyCube-Map computation includes feature-aware PolyCube-Map construction and cut-enhanced PolyCube deformation. The former aims to preserve input feature edges during the initial PolyCube-Map construction. The latter introduces seams into the volumetric PolyCube shape by cutting it through selective PolyCube edges and deforms the modified PolyCube under the seamless constraints to compute a low-distortion PolyCube-Map. The hexahedral mesh induced by the final PolyCube-Map can be further enhanced by our mesh improvement algorithm. We validate the efficacy of our method on a collection of more than one hundred CAD models and demonstrate its advantages over other automatic all-hex meshing methods and padding strategies. The limitations of cut-enhanced PolyCube-Maps are also discussed thoroughly.

We present ”CrowbarLimbs”, a new method with two deformable extending virtual limbs for text entry in virtual reality (VR) which relies on a crowbar-like metaphor. Text entry is the basis of many applications but remains challenging in VR environments, where some body parts of a user may quickly get fatigued by using previous selection-based methods [Speicher et al. 2018], such as the ray metaphor [Lee and Kim 2017] and ”DrumStick” [Doronichev 2016]. By adding two deformable virtual limbs and placing the virtual keyboard at a user-preferred location, our method can help users to place their hands in a comfortable posture, thus reducing the physical fatigue of different body parts, such as arms and shoulders. To the best knowledge of ours, previous text entry papers have not yet discussed which metaphor is more suitable for reducing physical fatigue. We thus introduce “CrowbarLimbs” to allow less fatigue, good system usability, and comparable text entry speed/accuracy to previous methods.

The planar COTS map proposed here takes the unit square to a region R bounded by four log-spiral edges. It is Corner-operated (controlled by the four corners of R) and Tran-similar (it maps translations to similarities). The tiles of the COTS map of a regular pattern are similar to each other. It may facilitate intuitive design and algorithmic optimization of procedural models of complex, possibly multi-resolution, lattices, because it affords constant-cost algorithms for Point-in-Lattice testing and for Total-Area-Calculations. We provide simple, closed-form expressions for evaluating the COTS map and its inverse from the positions of its corners. We conjecture that the COTS map may be useful in a variety of applications in Engineering, Architecture, and Art, and we provide a few illustrative examples of its possibilities. We compare it to related, previously proposed, planar maps and discuss several variations and extensions.

Vector graphics formats offer support for both filled and stroked primitives. Filled primitives paint all points in the region bounded by a set of outlines. Stroked primitives paint all points covered by a line drawn over the outlines. Editors allow users to convert stroked primitives to the outlines of equivalent filled primitives for further editing. Likewise, renderers typically convert stroked primitives to equivalent filled primitives prior to rendering. This conversion problem is deceivingly difficult to solve. Surprisingly, it has received little to no attention in the literature. Existing implementations output too many segments, do not satisfy accuracy requirements, or fail under a variety of conditions, often spectacularly. In this paper, we present a solution to the stroke-to-fill conversion problem that addresses these issues. One of our key insights is to take into account the evolutes of input outlines, in addition to their offsets, in regions of high curvature. Furthermore, our approach strives to maintain continuity between the input and the set of painted points. Our implementation is available in open source.

Multiple importance sampling (MIS) is a provably good way to combine a finite set of sampling techniques to reduce variance in Monte Carlo integral estimation. However, there exist integration problems for which a continuum of sampling techniques is available. To handle such cases we establish a continuous MIS (CMIS) formulation as a generalization of MIS to uncountably infinite sets of techniques. Our formulation is equipped with a base estimator that is coupled with a provably optimal balance heuristic and a practical stochastic MIS (SMIS) estimator that makes CMIS accessible to a broad range of problems. To illustrate the effectiveness and utility of our framework, we apply it to three different light transport applications, showing improved performance over the prior state-of-the-art techniques.

We propose to enhance the capability of standard free-surface flow simulators with efficient support for immersed bubbles through two new models: constraint-based bubbles and affine fluid regions. Unlike its predecessors, our constraint-based model entirely dispenses with the need for advection or projection inside zero-density bubbles, with extremely modest additional computational overhead that is proportional to the surface area of all bubbles. This surface-only approach is easy to implement, realistically captures many familiar bubble behaviors, and even allows two or more distinct liquid bodies to correctly interact across completely unsimulated air. We augment this model with a per-bubble volume-tracking and correction framework to minimize the cumulative effects of gradual volume drift. To support bubbles with non-zero densities, we propose a novel reduced model for an irregular fluid region with a single pointwise incompressible affine vector field. This model requires only 11 interior velocity degrees of freedom per affine fluid region in 3D, and correctly reproduces buoyant, stationary, and sinking behaviors of a secondary fluid phase with non-zero density immersed in water. Since the pressure projection step in both the above schemes is a slightly modified Poisson-style system, we propose novel Multigrid-based preconditioners for Conjugate Gradients for fast numerical solutions of our new discretizations. Furthermore, we observe that by enforcing an incompressible affine vector field over a coalesced set of grid cells, our reduced model is effectively an irregular coarse super-cell. This offers a convenient and flexible adaptive coarsening strategy that integrates readily with the standard staggered grid approach for fluid simulation, yet supports coarsened regions that are arbitrary voxelized shapes, and provides an analytically divergence-free interior. We demonstrate its effectiveness with a new adaptive liquid simulator whose interior regions are coarsened into a mix of tiles with regular and irregular shapes.

We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.

Parquetry is the art and craft of decorating a surface with a pattern of differently colored veneers of wood, stone, or other materials. Traditionally, the process of designing and making parquetry has been driven by color, using the texture found in real wood only for stylization or as a decorative effect. Here, we introduce a computational pipeline that draws from the rich natural structure of strongly textured real-world veneers as a source of detail to approximate a target image as faithfully as possible using a manageable number of parts. This challenge is closely related to the established problems of patch-based image synthesis and stylization in some ways, but fundamentally different in others. Most importantly, the limited availability of resources (any piece of wood can only be used once) turns the relatively simple problem of finding the right piece for the target location into the combinatorial problem of finding optimal parts while avoiding resource collisions. We introduce an algorithm that efficiently solves an approximation to the problem. It further addresses challenges like gamut mapping, feature characterization, and the search for fabricable cuts. We demonstrate the effectiveness of the system by fabricating a selection of pieces of parquetry from different kinds of unstained wood veneer.

Laser irradiation induces colors on some industrially important materials, such as stainless steel and titanium. It is however challenging to find marking configurations that create colorful, high-resolution images. The brute-force solution to the gamut exploration problem does not scale with the high-dimensional design space of laser marking. Moreover, there exists no color reproduction workflow capable of reproducing color images with laser marking. Here, we propose a measurement-based, data-driven performance space exploration of the color laser marking process. We formulate this exploration as a search for the Pareto optimal solutions to a multi-objective optimization and solve it using an evolutionary algorithm. The explored set of diverse colors is then utilized to mark high-quality, full-color images.

We propose an optimization-driven approach for automated, physics-based pattern design for tight-fitting clothing. Designing such clothing poses particular challenges since large nonlinear deformations, tight contact between cloth and body, and body deformations have to be accounted for. To address these challenges, we develop a computational model based on an embedding of the two-dimensional cloth mesh in the surface of the three-dimensional body mesh. Our Lagrangian-on-Lagrangian approach eliminates contact handling while coupling cloth and body. Building on this model, we develop a physics-driven optimization method based on sensitivity analysis that automatically computes optimal patterns according to design objectives encoding body shape, pressure distribution, seam traction, and other criteria. We demonstrate our approach by generating personalized patterns for various body shapes and a diverse set of garments with complex pattern layouts.

We present a technique for adaptively partitioning neural scene representations. Our method disentangles lighting, material, and geometric information yielding a scene representation that preserves the orthogonality of these components, improves interpretability of the model, and allows compositing new scenes by mixing components of existing ones. The proposed adaptive partitioning respects the uneven entropy of individual components and permits compressing the scene representation to lower its memory footprint and potentially reduce the evaluation cost of the model. Furthermore, the partitioned representation enables an in-depth analysis of existing image generators. We compare the flow of information through individual partitions, and by contrasting it to the impact of additional inputs (G-buffer), we are able to identify the roots of undesired visual artifacts, and propose one possible solution to remedy the poor performance. We also demonstrate the benefits of complementing traditional forward renderers by neural representations and synthesis, e.g. to infer expensive shading effects, and show how these could improve production rendering in the future if developed further.

Arrangements of geometric objects refer to the spatial partitions formed by the objects, and they serve as an underlining structure of motion design, analysis, and planning in CAD/CAM, robotics, molecular modeling, manufacturing, and computer-assisted radio-surgery. Arrangements are especially useful to collision detection, which is a key task in various applications such as computer animation, virtual reality, computer games, robotics, CAD/CAM, and computational physics. Ellipsoids are commonly used as bounding volumes in approximating complex geometric objects in collision detection. In this article, we present an in-depth study on the arrangements formed by two ellipsoids. Specifically, we present a classification of these arrangements and propose an efficient algorithm for determining the arrangement formed by any particular pair of ellipsoids. A stratification diagram is also established to show the connections among all the arrangements formed by two ellipsoids. Our results, for the first time, elucidate all possible relative positions between two arbitrary ellipsoids and provide an efficient and robust algorithm for determining the relative position of any two given ellipsoids, therefore providing the necessary foundation for developing practical and trustworthy methods for processing ellipsoids for collision analysis or simulation in various applications.

Fused filament fabrication is the method of choice for printing 3D models at low cost and is the de facto standard for hobbyists, makers, and schools. Unfortunately, filament printers cannot truly reproduce colored objects. The best current techniques rely on a form of dithering exploiting occlusion, which was only demonstrated for shades of two base colors and behaves differently depending on surface slope. We explore a novel approach for 3D-printing colored objects, capable of creating controlled gradients of varying sharpness. Our technique exploits off-the-shelf nozzles that are designed to mix multiple filaments in a small melting chamber, obtaining intermediate colors once the mix is stabilized. We apply this property to produce color gradients. We divide each input layer into a set of strata, each having a different constant color. By locally changing the thickness of the stratum, we change the perceived color at a given location. By optimizing the choice of colors of each stratum, we further improve quality and allow the use of different numbers of input filaments. We demonstrate our results by building a functional color printer using low-cost, off-the-shelf components. Using our tool, a user can paint a 3D model and directly produce its physical counterpart using any material and color available for fused filament fabrication.

We propose a new Eulerian-Lagrangian approach to simulate the various surface tension phenomena characterized by volume, thin sheets, thin filaments, and points using Moving-Least-Squares (MLS) particles. At the center of our approach is a meshless Lagrangian description of the different types of codimensional geometries and their transitions using an MLS approximation. In particular, we differentiate the codimension-1 and codimension-2 geometries on Lagrangian MLS particles to precisely describe the evolution of thin sheets and filaments, and we discretize the codimension-0 operators on a background Cartesian grid for efficient volumetric processing. Physical forces including surface tension and pressure across different codimensions are coupled in a monolithic manner by solving one single linear system to evolve the surface-tension driven Navier-Stokes system in a complex non-manifold space. The codimensional transitions are handled explicitly by tracking a codimension number stored on each particle, which replaces the tedious meshing operators in a conventional mesh-based approach. Using the proposed framework, we simulate a broad array of visually appealing surface tension phenomena, including the fluid chain, bell, polygon, catenoid, and dripping, to demonstrate the efficacy of our approach in capturing the complex fluid characteristics with mixed codimensions, in a robust, versatile, and connectivity-free manner.

Being able to duplicate published research results is an important process of conducting research whether to build upon these findings or to compare with them. This process is called "replicability" when using the original authors' artifacts (e.g., code), or "reproducibility" otherwise (e.g., re-implementing algorithms). Reproducibility and replicability of research results have gained a lot of interest recently with assessment studies being led in various fields, and they are often seen as a trigger for better result diffusion and transparency. In this work, we assess replicability in Computer Graphics, by evaluating whether the code is available and whether it works properly. As a proxy for this field we compiled, ran and analyzed 151 codes out of 374 papers from 2014, 2016 and 2018 SIGGRAPH conferences. This analysis shows a clear increase in the number of papers with available and operational research codes with a dependency on the subfields, and indicates a correlation between code replicability and citation count. We further provide an interactive tool to explore our results and evaluation data.

Soap bubbles are widely appreciated for their fragile nature and their colorful appearance. The natural sciences and, in extension, computer graphics, have comprehensively studied the mechanical behavior of films and foams, as well as the optical properties of thin liquid layers. In this paper, we focus on the dynamics of material flow within the soap film, which results in fascinating, extremely detailed patterns. This flow is characterized by a complex coupling between surfactant concentration and Marangoni surface tension. We propose a novel chemomechanical simulation framework rooted in lubrication theory, which makes use of a custom semi-Lagrangian advection solver to enable the simulation of soap film dynamics on spherical bubbles both in free flow as well as under body forces such as gravity or external air flow. By comparing our simulated outcomes to videos of real-world soap bubbles recorded in a studio environment, we show that our framework, for the first time, closely recreates a wide range of dynamic effects that are also observed in experiment.

A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven generative models of human movement using autoregressive conditional variational autoencoders, or Motion VAEs. The latent variables of the learned autoencoder define the action space for the movement and thereby govern its evolution over time. Planning or control algorithms can then use this action space to generate desired motions. In particular, we use deep reinforcement learning to learn controllers that achieve goal-directed movements. We demonstrate the effectiveness of the approach on multiple tasks. We further evaluate system-design choices and describe the current limitations of Motion VAEs.