SIGGRAPH 2020 论文列表

Creating animated virtual AR characters closely interacting with real environments is interesting but difficult. Existing systems adopt video see-through approaches to indirectly control a virtual character in mobile AR, making close interaction with real environments not intuitive. In this work we use an AR-enabled mobile device to directly control the position and motion of a virtual character situated in a real environment. We conduct two guessability studies to elicit user-defined motions of a virtual character interacting with real environments, and a set of user-defined motion gestures describing specific character motions. We found that an SVM-based learning approach achieves reasonably high accuracy for gesture classification from the motion data of a mobile device. We present ARAnimator, which allows novice and casual animation users to directly represent a virtual character by an AR-enabled mobile phone and control its animation in AR scenes using motion gestures of the device, followed by animation preview and interactive editing through a video see-through interface. Our experimental results show that with ARAnimator, users are able to easily create in-situ character animations closely interacting with different real environments.

Computer animation in conjunction with 3D printing has the potential to positively impact traditional stop-motion animation. As 3D printing every frame of a computer animation is prohibitively slow and expensive, 3D printed stop-motion can only be viable if animations can be faithfully reproduced using a compact library of 3D printed and efficiently assemblable parts. We thus present the first system for processing computer animation sequences (typically faces) to produce an optimal set of replacement parts for use in 3D printed stop-motion animation. Given an input animation sequence of topology invariant deforming meshes, our problem is to output a library of replacement parts and per-animation-frame assignment of the parts, such that we maximally approximate the input animation, while minimizing the amount of 3D printing and assembly. Inspired by current stop-motion workflows, a user manually indicates which parts of the model are preferred for segmentation; then, we find curves with minimal deformation along which to segment the mesh. We then present a novel algorithm to zero out deformations along the segment boundaries, so that replacement sets for each part can be interchangeably and seamlessly assembled together. The part boundaries are designed to ease 3D printing and instrumentation for assembly. Each part is then independently optimized using a graph-cut technique to find a set of replacements, whose size can be user defined, or automatically computed to adhere to a printing budget or allowed deviation from the original animation. Our evaluation is threefold: we show results on a variety of facial animations, both digital and 3D printed, critiqued by a professional animator; we show the impact of various algorithmic parameters; and we compare our results to naive solutions. Our approach can reduce the printing time and cost significantly for stop-motion animated films.

Current quadratic smoothness energies for curved surfaces either exhibit distortions near the boundary due to zero Neumann boundary conditions or they do not correctly account for intrinsic curvature, which leads to unnatural-looking behavior away from the boundary. This leads to an unfortunate trade-off: One can either have natural behavior in the interior or a distortion-free result at the boundary, but not both. We introduce a generalized Hessian energy for curved surfaces, expressed in terms of the covariant one-form Dirichlet energy, the Gaussian curvature, and the exterior derivative. Energy minimizers solve the Laplace-Beltrami biharmonic equation, correctly accounting for intrinsic curvature, leading to natural-looking isolines. On the boundary, minimizers are as-linear-as-possible, which reduces the distortion of isolines at the boundary. We discretize the covariant one-form Dirichlet energy using Crouzeix-Raviart finite elements, arriving at a discrete formulation of the Hessian energy for applications on curved surfaces. We observe convergence of the discretization in our experiments.

Figure 1: The model of Belcour [Belcour 2018] suffers from severe energy losses with scattering volumes due to its singlescattering approximation and its lack of support for back-scattering. Our transfer matrix approach overcomes these issues and provides results close to the ground-truth computed with Guo’s stochastic approach [Guo et al. 2018]. In these examples, a unit depth non-absorbing medium with scattering coefficient σs = 0.755 and varying Henyey-Greenstein (HG) д parameters lies on top of a smooth gold substrate. HG д asymmetry parameter is respectively set to 0.9 and to 0 in the left and right inset.

Human characters with a broad range of natural looking and physically realistic behaviors will enable the construction of compelling interactive experiences. In this paper, we develop a technique for learning controllers for a large set of heterogeneous behaviors. By dividing a reference library of motion into clusters of like motions, we are able to construct experts, learned controllers that can reproduce a simulated version of the motions in that cluster. These experts are then combined via a second learning phase, into a general controller with the capability to reproduce any motion in the reference library. We demonstrate the power of this approach by learning the motions produced by a motion graph constructed from eight hours of motion capture data and containing a diverse set of behaviors such as dancing (ballroom and breakdancing), Karate moves, gesturing, walking, and running.

We propose a new adaptive liquid simulation framework that achieves highly detailed behavior with reduced implementation complexity. Prior work has shown that spatially adaptive grids are efficient for simulating large-scale liquid scenarios, but in order to enable adaptivity along the liquid surface these methods require either expensive boundary-conforming (re-)meshing or elaborate treatments for second order accurate interface conditions. This complexity greatly increases the difficulty of implementation and maintainability, potentially making it infeasible for practitioners. We therefore present new algorithms for adaptive simulation that are comparatively easy to implement yet efficiently yield high quality results. First, we develop a novel staggered octree Poisson discretization for free surfaces that is second order in pressure and gives smooth surface motions even across octree T-junctions, without a power/Voronoi diagram construction. We augment this discretization with an adaptivity-compatible surface tension force that likewise supports T-junctions. Second, we propose a moving least squares strategy for level set and velocity interpolation that requires minimal knowledge of the local tree structure while blending near-seamlessly with standard trilinear interpolation in uniform regions. Finally, to maximally exploit the flexibility of our new surface-adaptive solver, we propose several novel extensions to sizing function design that enhance its effectiveness and flexibility. We perform a range of rigorous numerical experiments to evaluate the reliability and limitations of our method, as well as demonstrating it on several complex high-resolution liquid animation scenarios.

Limited GPU performance budgets and transmission bandwidths mean that real-time rendering often has to compromise on the spatial resolution or temporal resolution (refresh rate). A common practice is to keep either the resolution or the refresh rate constant and dynamically control the other variable. But this strategy is non-optimal when the velocity of displayed content varies. To find the best trade-off between the spatial resolution and refresh rate, we propose a perceptual visual model that predicts the quality of motion given an object velocity and predictability of motion. The model considers two motion artifacts to establish an overall quality score: non-smooth (juddery) motion, and blur. Blur is modeled as a combined effect of eye motion, finite refresh rate and display resolution. To fit the free parameters of the proposed visual model, we measured eye movement for predictable and unpredictable motion, and conducted psychophysical experiments to measure the quality of motion from 50 Hz to 165 Hz. We demonstrate the utility of the model with our on-the-fly motion-adaptive rendering algorithm that adjusts the refresh rate of a G-Sync-capable monitor based on a given rendering budget and observed object motion. Our psychophysical validation experiments demonstrate that the proposed algorithm performs better than constant-refresh-rate solutions, showing that motion-adaptive rendering is an attractive technique for driving variable-refresh-rate displays.

In this work, we present a method to turn still life paintings with global illumination effects into dynamic paintings with moving lights. Our method specifically focuses on still life images containing (1) glass objects, which can have specular highlights with Fresnel effect and (2) fruits, which can have reflection and subsurface scattering. Our goal is to preserve the original look-and-feel of the still-life paintings while allowing the user to move the light source anywhere in the scene, causing the shadows, diffuse shading, as well as reflections and specular highlights to move according to the new light position. We have provided a proof of concept based on an original digital painting. This method can be used to turn any similar still life painting into a dynamic painting.

Previous research on animations of soap bubbles, films, and foams largely focuses on the motion and geometric shape of the bubble surface. These works neglect the evolution of the bubble's thickness, which is normally responsible for visual phenomena like surface vortices, Newton's interference patterns, capillary waves, and deformation-dependent rupturing of films in a foam. In this paper, we model these natural phenomena by introducing the film thickness as a reduced degree of freedom in the Navier-Stokes equations and deriving their equations of motion. We discretize the equations on a non-manifold triangle mesh surface and couple it to an existing bubble solver. In doing so, we also introduce an incompressible fluid solver for 2.5D films and a novel advection algorithm for convecting fields across non-manifold surface junctions. Our simulations enhance state-of-the-art bubble solvers with additional effects caused by convection, rippling, draining, and evaporation of the thin film.

(a) Viewing from the user , the hand is in front of the mid-air 3DCG object, so the hand is occluding the 3DCG object. (b) Viewing from the user, part of the hand is behind the mid-air 3DCG object. Occluding the hand with the mid-air 3DCG object realized by projecting an appropriate image to the hand automatically. (c) Another example of occluding the hand with the mid-air 3DCG object based on projecting an image.

Harnessing the power of modern multi-GPU architectures, we present a massively parallel simulation system based on the Material Point Method (MPM) for simulating physical behaviors of materials undergoing complex topological changes, self-collision, and large deformations. Our system makes three critical contributions. First, we introduce a new particle data structure that promotes coalesced memory access patterns on the GPU and eliminates the need for complex atomic operations on the memory hierarchy when writing particle data to the grid. Second, we propose a kernel fusion approach using a new Grid-to-Particles-to-Grid (G2P2G) scheme, which efficiently reduces GPU kernel launches, improves latency, and significantly reduces the amount of global memory needed to store particle data. Finally, we introduce optimized algorithmic designs that allow for efficient sparse grids in a shared memory context, enabling us to best utilize modern multi-GPU computational platforms for hybrid Lagrangian-Eulerian computational patterns. We demonstrate the effectiveness of our method with extensive benchmarks, evaluations, and dynamic simulations with elastoplasticity, granular media, and fluid dynamics. In comparisons against an open-source and heavily optimized CPU-based MPM codebase [Fang et al. 2019] on an elastic sphere colliding scene with particle counts ranging from 5 to 40 million, our GPU MPM achieves over 100x per-time-step speedup on a workstation with an Intel 8086K CPU and a single Quadro P6000 GPU, exposing exciting possibilities for future MPM simulations in computer graphics and computational science. Moreover, compared to the state-of-the-art GPU MPM method [Hu et al. 2019a], we not only achieve 2x acceleration on a single GPU but our kernel fusion strategy and Array-of-Structs-of-Array (AoSoA) data structure design also generalizes to multi-GPU systems. Our multi-GPU MPM exhibits near-perfect weak and strong scaling with 4 GPUs, enabling performant and large-scale simulations on a 10243 grid with close to 100 million particles with less than 4 minutes per frame on a single 4-GPU workstation and 134 million particles with less than 1 minute per frame on an 8-GPU workstation.

The perceived discrepancy between continuous motion as seen in nature and frame-by-frame exhibition on a display, sometimes termed judder, is an integral part of video presentation. Over time, content creators have developed a set of rules and guidelines for maintaining a desirable cinematic look under the restrictions placed by display technology without incurring prohibitive judder. With the advent of novel displays capable of high brightness, contrast, and frame rates, these guidelines are no longer sufficient to present audiences with a uniform viewing experience. In this work, we analyze the main factors for perceptual motion artifacts in digital presentation and gather psychophysical data to generate a model of judder perception. Our model enables applications like matching perceived motion artifacts to a traditionally desirable level and maintain a cinematic motion look.

New fabrication technologies have significantly decreased the cost of fabrication of shapes with highly complex geometric structure. One important application of complex fine-scale geometric structures is to create variable effective elastic material properties in shapes manufactured from a single material. Modification of material properties has a variety of uses, from aerospace applications to soft robotics and prosthetic devices. Due to its scalability and effectiveness, an increasingly common approach to creating spatially varying materials is to partition a shape into cells and use a parametric family of small-scale geometric structures with known effective properties to fill the cells. We propose a new approach to solving this problem for extruded, planar microstructures. Differently from existing methods for two-scale optimization based on regular grids with square periodic cells, which cannot conform to an arbitrary boundary, we introduce cell decompositions consisting of (nearly) rhombic cells. These meshes have far greater flexibility than those with square cells in terms of approximating arbitrary shapes, and, at the same time, have a number of properties simplifying small-scale structure construction. Our main contributions include a new family of 2D cell geometry structures, explicitly parameterized by their effective Young's moduli E, Poisson's ratios v, and rhombic angle α with the geometry parameters expressed directly as smooth spline functions of E, v, and α. This family leads to smooth transitions between the tiles and can handle a broad range of rhombic cell shapes. We introduce a complete material design pipeline based on this microstructure family, composed of an algorithm to generate rhombic tessellation from quadrilateral meshes and an algorithm to synthesize the microstructure geometry. We fabricated a number of models and experimentally demonstrated how our method, in combination with material optimization, can be used to achieve the desired deformation behavior.

We present a versatile numerical approach to simulating various magnetic phenomena using a level-set method. At the heart of our method lies a novel two-way coupling mechanism between a magnetic field and a magnetizable mechanical system, which is based on the interfacial Helmholtz force drawn from the Minkowski form of the Maxwell stress tensor. We show that a magnetic-mechanical coupling system can be solved as an interfacial problem, both theoretically and computationally. In particular, we employ a Poisson equation with a jump condition across the interface to model the mechanical-to-magnetic interaction and a Helmholtz force on the free surface to model the magnetic-to-mechanical effects. Our computational framework can be easily integrated into a standard Euler fluid solver, enabling both simulation and visualization of a complex magnetic field and its interaction with immersed magnetizable objects in a large domain. We demonstrate the efficacy of our method through an array of magnetic substance simulations that exhibit rich geometric and dynamic characteristics, encompassing ferrofluid, rigid magnetic body, deformable magnetic body, and multi-phase couplings.

Although artists’ actions in photo retouching appear to be highly nonlinear in nature and very difficult to characterize analytically, we find that the net effects of interactively editing a mundane image to a desired appearance can be modeled, in most cases, by a parametric monotonically non-decreasing global tone mapping function in the luminance axis and by a global affine transform in the chrominance plane. This allows us to greatly simplify the existing CNN methods for mimicking the artists in photo retouching, and design a new artful image regeneration network (AIRNet). The objective of AIRNet is to learn the image-dependent parameters of the luminance tone mapping function and the affine chrominance transform, rather than learning the end-to-end pixel level mapping as in the standard practice of current CNN methods for image restoration and enhancement. The proposed new approach reduces the complexity of the neural network by two orders of magnitude, and as a side benefit, it also improves the robustness and the generation capability at the inference stage.

We present a class of non-polynomial parametric splines that interpolate the given control points and show that some curve types in this class have a set of highly desirable properties that were not previously demonstrated for interpolating curves before. In particular, the formulation of this class guarantees that the resulting curves have C2 continuity everywhere and local support, such that only four control points define each curve segment between consecutive control points. These properties are achieved directly due to the mathematical formulation used for defining this class, without the need for a global numerical optimization step. We also provide four example spline types within this class. These examples show how guaranteed self-intersection-free curve segments can be achieved, regardless of the placement of control points, which has been a limitation of prior interpolating curve formulations. In addition, they present how perfect circular arcs and linear segments can be formed by splines within this class, which also have been challenging for prior methods of interpolating curves.

This poster describes the implementation of a performant 2D drawing application in the browser that renders Signed Distance Functions (SDF) compiled from user input. SDFs are well suited for CAD applications because they reveal elegant boolean operations and efficiently allow for superior anti-aliasing. Because of their reliance on the GPU, SDFs have not traditionally lent themselves to graphical user input. By compiling shaders on the fly from user input we are able to seamlessly interact with rendered SDFs in a CAD interface.