SIGGRAPH 2019 论文列表

It is well known that the dynamics of articulated rigid bodies can be solved in O(n) time using a recursive method, where n is the number of joints. However, when elasticity is added between the bodies (e.g., damped springs), with linearly implicit integration, the stiffness matrix in the equations of motion breaks the tree topology of the system, making the recursive O(n) method inapplicable. In such cases, the only alternative has been to form and solve the system matrix, which takes O(n3) time. We propose a new approach that is capable of solving the linearly implicit equations of motion in near linear time. Our method, which we call RedMax, is built using a combined reduced/maximal coordinate formulation. This hybrid model enables direct flexibility to apply arbitrary combinations of constraints and contact modeling in both reduced and maximal coordinates, as well as mixtures of implicit and explicit forces in either coordinate representation. We highlight RedMax's flexibility with seamless integration of deformable objects with two-way coupling, at a standard additional cost. We further highlight its flexibility by constructing an efficient internal (joint) and external (environment) frictional contact solver that can leverage bilateral joint constraints for rapid evaluation of frictional articulated dynamics.

The Ouija board game is associated with a type of involuntary motion known as an ideomotor action. We sought to clarify the conditions under which this motion occurs by evaluating the effect that visual and haptic movement cues have on its occurrence. Using our lateral skin deformation device, we found that the simultaneous presentation of visual and tactile illusory motion and force produced larger ideomotor actions than when either modality presented alone, an effect that was further potentiated by the presence of another player (an avatar).

In computer graphics, stippling is a widely used non-photorealistic rendering technique. As the art of representing images with dots, one of the key problems is the placement of dots. In general, they should be distributed evenly, and with some randomness at the same time. Blue noise methods provide these characteristics and are used by state-of-the-art gray-scale algorithms to distribute dots. Color stippling, however, is more challenging as each channel should have even distribution at the same time. Existing approaches cast color stippling as a multi-class blue noise sampling problem and provide high quality results at the cost of a very long processing time. In this paper, we propose a real-time structure aware method for color stippling, based on samples generated from an incremental voronoi set. Our method can handle an arbitrary input color vector for stippling and produce significantly better results than previous methods, at real-time frame rate. We evaluate the perceptual quality of our stippling with a user study and its numerical performance by measuring the MSE between the reconstructed image from the stippling and the input image. As a result, the real time performance of our method makes interactive stippling editing possible, providing the artist with an effective tool to explore quickly a wide space of color image stippling.

We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands. Our approach is the first two-hand tracking solution that combines an extensive list of favorable properties, namely it is marker-less, uses a single consumer-level depth camera, runs in real time, handles inter- and intra-hand collisions, and automatically adjusts to the user's hand shape. In order to achieve this, we embed a recent parametric hand pose and shape model and a dense correspondence predictor based on a deep neural network into a suitable energy minimization framework. For training the correspondence prediction network, we synthesize a two-hand dataset based on physical simulations that includes both hand pose and shape annotations while at the same time avoiding inter-hand penetrations. To achieve real-time rates, we phrase the model fitting in terms of a nonlinear least-squares problem so that the energy can be optimized based on a highly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art results in scenes that exceed the complexity level demonstrated by previous work, including tight two-hand grasps, significant inter-hand occlusions, and gesture interaction.1

This paper proposes an intuitive tool for users to create 3D architectural models through 2D sketch input. A user only needs to draw the outline of a frontal or oblique view of a building. Our system recognizes the parts drawn in a sketch and estimates their types. The estimated information is then used to compose the corresponding 3D model. Besides, our system provides additional assistant tools for rapid editing. The modeling process can be iterative and incremental. To accomplish a building complex, a user can gradually create their models from one view to another. Our experiment shows that the proposed interface with sketch analysis tools eases the process of 3D building modeling.

Light projection onto falling water produces distinct and impressive experience which is suitable for entertainment and advertising installations in public spaces [Barnum et al. 2010; Eitoku et al. 2006]. One of popular and classical techniques used in illuminating water for such purposes is strobe lighting, which presents optical illusion of levitating --- or slowly falling or rising --- water drops depending on the relation between water dropping and strobe lighting frequencies (e.g. [Pevnick 1981; Rosenthal 1984]).

Tutte embedding is one of the most common building blocks in geometry processing algorithms due to its simplicity and provable guarantees. Although provably correct in infinite precision arithmetic, it fails in challenging cases when implemented using floating point arithmetic, largely due to the induced exponential area changes. We propose Progressive Embedding, with similar theoretical guarantees to Tutte embedding, but more resilient to the rounding error of floating point arithmetic. Inspired by progressive meshes, we collapse edges on an invalid embedding to a valid, simplified mesh, then insert points back while maintaining validity. We demonstrate the robustness of our method by computing embeddings for a large collection of disk topology meshes. By combining our robust embedding with a variant of the matchmaker algorithm, we propose a general algorithm for the problem of mapping multiply connected domains with arbitrary hard constraints to the plane, with applications in texture mapping and remeshing.

We propose a new algorithm for color transfer between images that have perceptually similar semantic structures. We aim to achieve a more accurate color transfer that leverages semantically meaningful dense correspondence between images. To accomplish this, our algorithm uses neural representations for matching. Additionally, the color transfer should be spatially variant and globally coherent. Therefore, our algorithm optimizes a local linear model for color transfer satisfying both local and global constraints. Our proposed approach jointly optimizes matching and color transfer, adopting a coarse-to-fine strategy. The proposed method can be successfully extended from one-to-one to one-to-many color transfer. The latter further addresses the problem of mismatching elements of the input image. We validate our proposed method by testing it on a large variety of image content.

Procedural pattern synthesis is a fundamental tool of Computer Graphics, ubiquitous in games and special effects. By calling a single procedure in every pixel - or voxel - large quantities of details are generated at low cost, enhancing textures, producing complex structures within and along surfaces. Such procedures are typically implemented as pixel shaders. We propose a novel procedural pattern synthesis technique that exhibits desirable properties for modeling highly contrasted patterns, that are especially well suited to produce surface and microstructure details. In particular, our synthesizer affords for a precise control over the profile, orientation and distribution of the produced stochastic patterns, while allowing to grade all these parameters spatially. Our technique defines a stochastic smooth phase field - a phasor noise - that is then fed into a periodic function (e.g. a sine wave), producing an oscillating field with prescribed main frequencies and preserved contrast oscillations. In addition, the profile of each oscillation is directly controllable (e.g. sine wave, sawtooth, rectangular or any 1D profile). Our technique builds upon a reformulation of Gabor noise in terms of a phasor field that affords for a clear separation between local intensity and phase. Applications range from texturing to modeling surface displacements, as well as multi-material microstructures in the context of additive manufacturing.

Accurate modeling and rendering of human skin appearance has been a long standing goal in computer graphics. Of particular importance has been the realistic modeling and rendering of layered subsurface scattering in skin for which various bio-physical models have been proposed based on the spectral distribution of chromophores in the epidermal and dermal layers of skin [Donner and Jensen 2006; Donner et al. 2008; Jimenez et al. 2010]. However, measurement of the spectral parameters of absorption and scattering of light for such bio-phyisical models has been a challenge in computer graphics. Previous works have either borrowed parameters for skin-type from tissue-optics literature [Donner and Jensen 2006], or employed extensive multispectral imaging for inverse rendering detailed spatially varying parameters for a patch of skin [Donner et al. 2008]. Closest to our approach, Jimenez et al. [2010] employed observations under uniform broadband illumination to estimate two dominant parameters (melanin and hemoglobin concentrations) for driving a qualitative appearance model for facial animation.

We present a new framework for interior scene synthesis that combines a high-level relation graph representation with spatial prior neural networks. We observe that prior work on scene synthesis is divided into two camps: object-oriented approaches (which reason about the set of objects in a scene and their configurations) and space-oriented approaches (which reason about what objects occupy what regions of space). Our insight is that the object-oriented paradigm excels at high-level planning of how a room should be laid out, while the space-oriented paradigm performs well at instantiating a layout by placing objects in precise spatial configurations. With this in mind, we present PlanIT, a layout-generation framework that divides the problem into two distinct planning and instantiation phases. PlanIT represents the "plan" for a scene via a relation graph, encoding objects as nodes and spatial/semantic relationships between objects as edges. In the planning phase, it uses a deep graph convolutional generative model to synthesize relation graphs. In the instantiation phase, it uses image-based convolutional network modules to guide a search procedure that places objects into the scene in a manner consistent with the graph. By decomposing the problem in this way, PlanIT generates scenes of comparable quality to those generated by prior approaches (as judged by both people and learned classifiers), while also providing the modeling flexibility of the intermediate relationship graph representation. These graphs allow the system to support applications such as scene synthesis from a partial graph provided by a user.

We introduce a new method that efficiently computes a set of viewpoints and trajectories for high-quality 3D reconstructions in outdoor environments. Our goal is to automatically explore an unknown area and obtain a complete 3D scan of a region of interest (e.g., a large building). Images from a commodity RGB camera, mounted on an autonomously navigated quadcopter, are fed into a multi-view stereo reconstruction pipeline that produces high-quality results but is computationally expensive. In this setting, the scanning result is constrained by the restricted flight time of quadcopters. To this end, we introduce a novel optimization strategy that respects these constraints by maximizing the information gain from sparsely sampled viewpoints while limiting the total travel distance of the quadcopter. At the core of our method lies a hierarchical volumetric representation that allows the algorithm to distinguish between unknown, free, and occupied space. Furthermore, our information gain-based formulation leverages this representation to handle occlusions in an efficient manner. In addition to the surface geometry, we utilize free-space information to avoid obstacles and determine collision-free flight paths. Our tool can be used to specify the region of interest and to plan trajectories. We demonstrate our method by obtaining a number of compelling 3D reconstructions, and we provide a thorough quantitative evaluation showing improvement over previous state-of-the-art and regular patterns.

We present an educational virtual reality (VR) puzzle game set in an archaeological context. We digitally documented the site architecture and a selection of excavated artefact using structure from motion (SfM) mapping, reconstructed the site during Classic Period (AD 250-900) based on the current state and archaeological findings, and created the natural environment using procedural modeling. With this collection of resources, we created a holistic landscape of the Mayan site of Cahal Pech. The player can link the Mayan ruin between its current state and the past through collecting artefact and evidence, and discover the architectural beauty and historical richness of this site.

Playing with a soccer ball is not easy even for a real human because of dynamic foot contacts with the moving ball while chasing and controlling it. The problem of online full-body soccer motion synthesis is challenging and has not been fully solved yet. In this paper, we present a novel motion control system that produces physically-correct full-body soccer motions: dribbling forward, dribbling to the side, and shooting, in response to an online user motion prescription specified by a motion type, a running speed, and a turning angle. This system performs two tightly-coupled tasks: data-driven motion prediction and physics-based motion synthesis. Given example motion data, the former synthesizes a reference motion in accordance with an online user input and further refines the motion to make the character kick the ball at a right time and place. Provided with the reference motion, the latter then adopts a Model Predictive Control (MPC) framework to generate a physically-correct soccer motion, by solving an optimal control problem that is formulated based on dynamics for a full-body character and the moving ball together with their interactions. Our demonstration shows the effectiveness of the proposed system that synthesizes convincing full-body soccer motions in various scenarios such as adjusting the desired running speed of the character, changing the velocity and the mass of the ball, and maintaining balance against external forces.

To develop a graphics project with ease and confidence, the reliability and extensibility of the underlying framework are essential. While there are existing options, e.g., pbrt-v3 [Pharr et al. 2016] and Mitsuba [Jakob 2010], they either focus on education or not being updated for a long time. We would like to present an alternative solution named Photon.

We generalize photon planes to photon surfaces: a new family of unbiased volumetric density estimators which we combine using multiple importance sampling. To derive our new estimators, we start with the extended path integral which duplicates the vertex at the end of the camera and photon subpaths and couples them using a blurring kernel. To make our formulation unbiased, however, we use a delta kernel to couple these two end points. Unfortunately, sampling the resulting singular integral using Monte Carlo is impossible since the probability of generating a contributing light path by independently sampling the two subpaths is zero. Our key insight is that we can eliminate the delta kernel and make Monte Carlo estimation practical by integrating any three dimensions analytically, and integrating only the remaining dimensions using Monte Carlo. We demonstrate the practicality of this approach by instantiating a collection of estimators which analytically integrate the distance along the camera ray and two arbitrary sampling dimensions along the photon subpath (e.g., distance, direction, surface area). This generalizes photon planes to curved "photon surfaces", including new "photon cone", "photon cylinder", "photon sphere", and multiple new "photon plane" estimators. These estimators allow us to handle light paths not supported by photon planes, including single scattering, and surface-to-media transport. More importantly, since our estimators have complementary strengths due to analytically integrating different dimensions of the path integral, we can combine them using multiple importance sampling. This combination mitigates singularities present in individual estimators, substantially reducing variance while remaining fully unbiased. We demonstrate our improved estimators on a number of scenes containing homogeneous media with highly anisotropic phase functions, accelerating both multiple scattering and single scattering compared to prior techniques.