37-Issue 2

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632120

Browse

Now showing 1 - 20 of 29

Approximate Program Smoothing Using Mean-Variance Statistics, with Application to Procedural Shader Bandlimiting
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Yang, Yuting; Barnes, Connelly; Gutierrez, Diego and Sheffer, Alla
We introduce a general method to approximate the convolution of a program with a Gaussian kernel. This results in the program being smoothed. Our compiler framework models intermediate values in the program as random variables, by using mean and variance statistics. We decompose the input program into atomic parts and relate the statistics of the different parts of the smoothed program. We give several approximate smoothing rules that can be used for the parts of the program. These include an improved variant of Dorn et al. [DBLW15], a novel adaptive Gaussian approximation, Monte Carlo sampling, and compactly supported kernels. Our adaptive Gaussian approximation handles multivariate Gaussian distributed inputs, gives exact results for a larger class of programs than previous work, and is accurate to the second order in the standard deviation of the kernel for programs with certain analytic properties. Because each expression in the program can have multiple approximation choices, we use a genetic search to automatically select the best approximations. We apply this framework to the problem of automatically bandlimiting procedural shader programs. We evaluate our method on a variety of geometries and complex shaders, including shaders with parallax mapping, animation, and spatially varying statistics. The resulting smoothed shader programs outperform previous approaches both numerically and aesthetically.
Aura Mesh: Motion Retargeting to Preserve the Spatial Relationships between Skinned Characters
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Jin, Taeil; Kim, Meekyoung; Lee, Sung-Hee; Gutierrez, Diego and Sheffer, Alla
Applying motion-capture data to multi-person interaction between virtual characters is challenging because one needs to preserve the interaction semantics while also satisfying the general requirements of motion retargeting, such as preventing penetration and preserving naturalness. An efficient means of representing interaction semantics is by defining the spatial relationships between the body parts of characters. However, existing methods consider only the character skeleton and thus are not suitable for capturing skin-level spatial relationships. This paper proposes a novel method for retargeting interaction motions with respect to character skins. Specifically, we introduce the aura mesh, which is a volumetric mesh that surrounds a character's skin. The spatial relationships between two characters are computed from the overlap of the skin mesh of one character and the aura mesh of the other, and then the interaction motion retargeting is achieved by preserving the spatial relationships as much as possible while satisfying other constraints. We show the effectiveness of our method through a number of experiments.
Controllable Dendritic Crystal Simulation Using Orientation Field
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Ren, Bo; Huang, Jiahui; Lin, Ming C.; Hu, Shi-Min; Gutierrez, Diego and Sheffer, Alla
Real world dendritic growths show charming structures by their exquisite balance between the symmetry and randomness in the crystal formation. Other than the variety in the natural crystals, richer visual appearance of crystals can benefit from artificially controlling of the crystal growth on its growing directions and shapes. In this paper, by introducing one extra dimension of freedom, i.e. the orientation field, into the simulation, we propose an efficient algorithm for dendritic crystal simulation that is able to reproduce arbitrary symmetry patterns with different levels of asymmetry breaking effect on general grids or meshes, including spreading on curved surfaces and growth in 3D. Flexible artistic control is also enabled in a unified manner by exploiting and guiding the orientation field in the visual simulation. We show the effectiveness of our approach by various demonstrations of simulation results.
Deep Joint Design of Color Filter Arrays and Demosaicing
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Henz, Bernardo; Gastal, Eduardo S. L.; Oliveira, Manuel M.; Gutierrez, Diego and Sheffer, Alla
We present a convolutional neural network architecture for performing joint design of color filter array (CFA) patterns and demosaicing. Our generic model allows the training of CFAs of arbitrary sizes, optimizing each color filter over the entire RGB color space. The patterns and algorithms produced by our method provide high-quality color reconstructions. We demonstrate the effectiveness of our approach by showing that its results achieve higher PSNR than the ones obtained with state-of-the-art techniques on all standard demosaicing datasets, both for noise-free and noisy scenarios. Our method can also be used to obtain demosaicing strategies for pre-defined CFAs, such as the Bayer pattern, for which our results also surpass even the demosaicing algorithms specifically designed for such a pattern.
Efficient BVH-based Collision Detection Scheme with Ordering and Restructuring
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Wang, Xinlei; Tang, Min; Manocha, Dinesh; Tong, Ruofeng; Gutierrez, Diego and Sheffer, Alla
Bounding volume hierarchy (BVH) has been widely adopted as the acceleration structure in broad-phase collision detection. Previous state-of-the-art BVH-based collision detection approaches exploited the spatio-temporal coherence of simulations by maintaining a bounding volume test tree (BVTT) front. A major drawback of these algorithms is that large deformations in the scenes decrease culling efficiency and slow down collision queries. Moreover, for front-based methods, the inefficient caching on GPU caused by the arbitrary layout of BVH and BVTT front nodes becomes a critical performance issue. We present a fast and robust BVH-based collision detection scheme on GPU that addresses the above problems by ordering and restructuring BVHs and BVTT fronts. Our techniques are based on the use of histogram sort and an auxiliary structure BVTT front log, through which we analyze the dynamic status of BVTT front and BVH quality. Our approach efficiently handles inter- and intra-object collisions and performs especially well in simulations where there is considerable spatio-temporal coherence. The benchmark results demonstrate that our approach is significantly faster than the previous BVH-based method, and also outperforms other state-of-the-art spatial subdivision schemes in terms of speed.
Example-based Authoring of Procedural Modeling Programs with Structural and Continuous Variability
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Ritchie, Daniel; Jobalia, Sarah; Thomas, Anna; Gutierrez, Diego and Sheffer, Alla
Procedural models are a powerful tool for quickly creating a variety of computer graphics content. However, authoring them is challenging, requiring both programming and artistic expertise. In this paper, we present a method for learning procedural models from a small number of example objects. We focus on the modular design setting, where objects are constructed from a common library of parts. Our procedural representation is a probabilistic program that models both the discrete, hierarchical structure of the examples as well as the continuous variability in their spatial arrangements of parts. We develop an algorithm for learning such programs from examples, using combinatorial search over program structures and variational inference to estimate continuous program parameters. We evaluate our method by demonstrating its ability to learn programs from examples of ornamental designs, spaceships, space stations, and castles. Experiments suggest that our learned programs can reliably generate a variety of new objects that are perceptually indistinguishable from hand-crafted examples.
ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Marnerides, Demetris; Bashford-Rogers, Thomas; Hatchett, Jon; Debattista, Kurt; Gutierrez, Diego and Sheffer, Alla
High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.
Extended Narrow Band FLIP for Liquid Simulations
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Sato, Takahiro; Wojtan, Chris; Thuerey, Nils; Igarashi, Takeo; Ando, Ryoichi; Gutierrez, Diego and Sheffer, Alla
The Fluid Implicit Particle method (FLIP) reduces numerical dissipation by combining particles with grids. To improve performance, the subsequent narrow band FLIP method (NB-FLIP) uses a FLIP-based fluid simulation only near the liquid surface and a traditional grid-based fluid simulation away from the surface. This spatially-limited FLIP simulation significantly reduces the number of particles and alleviates a computational bottleneck. In this paper, we extend the NB-FLIP idea even further, by allowing a simulation to transition between a FLIP-like fluid simulation and a grid-based simulation in arbitrary locations, not just near the surface. This approach leads to even more savings in memory and computation, because we can concentrate the particles only in areas where they are needed. More importantly, this new method allows us to seamlessly transition to smooth implicit surface geometry wherever the particle-based simulation is unnecessary. Consequently, our method leads to a practical algorithm for avoiding the noisy surface artifacts associated with particle-based liquid simulations, while simultaneously maintaining the benefits of a FLIP simulation in regions of dynamic motion.
Fast Catmull-Rom Spline Interpolation for High-Quality Texture Sampling
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Csébfalvi, Balázs; Gutierrez, Diego and Sheffer, Alla
It is well known that cubic texture filtering can be efficiently implemented on the GPU by using a method published by Sigg and Hadwiger [SH05], which simplifies the evaluation to a linear combination of linear texture fetches. However, their method cannot be directly applied if the filter kernel takes also negative values like the popular Catmull-Rom spline, for example. In this paper, we propose a modified algorithm that is able to handle also the negative weights. Therefore, using our method, the Catmull-Rom spline interpolation can also be evaluated in one, two, and three dimensions by taking two, four, and eight linear texture fetches, respectively.
Fast Fluid Simulations with Sparse Volumes on the GPU
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Wu, Kui; Truong, Nghia; Yuksel, Cem; Hoetzlein, Rama; Gutierrez, Diego and Sheffer, Alla
We introduce efficient, large scale fluid simulation on GPU hardware using the fluid-implicit particle (FLIP) method over a sparse hierarchy of grids represented in NVIDIA R GVDB Voxels. Our approach handles tens of millions of particles within a virtually unbounded simulation domain. We describe novel techniques for parallel sparse grid hierarchy construction and fast incremental updates on the GPU for moving particles. In addition, our FLIP technique introduces sparse, work efficient parallel data gathering from particle to voxel, and a matrix-free GPU-based conjugate gradient solver optimized for sparse grids. Our results show that our method can achieve up to an order of magnitude faster simulations on the GPU as compared to FLIP simulations running on the CPU.
Fast Penetration Volume for Rigid Bodies
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Nirel, Dan; Lischinski, Dani; Gutierrez, Diego and Sheffer, Alla
Handling collisions among a large number of bodies can be a performance bottleneck in video games and many other real-time applications. We present a new framework for detecting and resolving collisions using the penetration volume as an interpenetration measure. Given two non-convex polyhedral bodies, a new sampling paradigm locates their near-contact configurations in advance, and stores associated contact information in a compact database. At runtime, we retrieve a given configuration's nearest neighbors. By taking advantage of the penetration volume's continuity, cheap geometric methods can use the neighbors to estimate contact information as well as a translational gradient. This results in an extremely fast, geometry-independent, and trivially parallelizable computation, which constitutes the first global volume-based collision resolution. When processing multiple collisions simultaneously on a 4-core processor, the average running cost is as low as 5 μs. Furthermore, no additional proximity or contact-regions queries are required. These results are orders of magnitude faster than previous penetration volume approaches.
Feature Curve Co-Completion in Noisy Data
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Gehre, Anne; Lim, Isaak; Kobbelt, Leif; Gutierrez, Diego and Sheffer, Alla
Feature curves on 3D shapes provide important hints about significant parts of the geometry and reveal their underlying structure. However, when we process real world data, automatically detected feature curves are affected by measurement uncertainty, missing data, and sampling resolution, leading to noisy, fragmented, and incomplete feature curve networks. These artifacts make further processing unreliable. In this paper we analyze the global co-occurrence information in noisy feature curve networks to fill in missing data and suppress weakly supported feature curves. For this we propose an unsupervised approach to find meaningful structure within the incomplete data by detecting multiple occurrences of feature curve configurations (cooccurrence analysis). We cluster and merge these into feature curve templates, which we leverage to identify strongly supported feature curve segments as well as to complete missing data in the feature curve network. In the presence of significant noise, previous approaches had to resort to user input, while our method performs fully automatic feature curve co-completion. Finding feature reoccurrences however, is challenging since naïve feature curve comparison fails in this setting due to fragmentation and partial overlaps of curve segments. To tackle this problem we propose a robust method for partial curve matching. This provides us with the means to apply symmetry detection methods to identify co-occurring configurations. Finally, Bayesian model selection enables us to detect and group re-occurrences that describe the data well and with low redundancy.
Hair Modeling and Simulation by Style
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Jung, Seunghwan; Lee, Sung-Hee; Gutierrez, Diego and Sheffer, Alla
As the deformation behaviors of hair strands vary greatly depending on the hairstyle, the computational cost and accuracy of hair movement simulations can be significantly improved by applying simulation methods specific to a certain style. This paper makes two contributions with regard to the simulation of various hair styles. First, we propose a novel method to reconstruct simulatable hair strands from hair meshes created by artists. Manually created hair meshes consist of numerous mesh patches, and the strand reconstruction process is challenged by the absence of connectivity information among the patches for the same strand and the omission of hidden parts of strands due to the manual creation process. To this end, we develop a two-stage spectral clustering method for estimating the degree of connectivity among patches and a strand-growing method that preserves hairstyles. Next, we develop a hairstyle classification method for style-specific simulations. In particular, we propose a set of features for efficient classifications and show that classifiers trained with the proposed features have higher accuracy than those trained with naive features. Our method applies efficient simulation methods according to the hairstyle without specific user input, and thus is favorable for real-time simulation.
Improved Functional Mappings via Product Preservation
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Nogneng, Dorian; Melzi, Simone; Rodolà, Emanuele; Castellani, Umberto; Bronstein, Michael; Ovsjanikov, Maks; Gutierrez, Diego and Sheffer, Alla
In this paper, we consider the problem of information transfer across shapes and propose an extension to the widely used functional map representation. Our main observation is that in addition to the vector space structure of the functional spaces, which has been heavily exploited in the functional map framework, the functional algebra (i.e., the ability to take pointwise products of functions) can significantly extend the power of this framework. Equipped with this observation, we show how to improve one of the key applications of functional maps, namely transferring real-valued functions without conversion to point-to-point correspondences. We demonstrate through extensive experiments that by decomposing a given function into a linear combination consisting not only of basis functions but also of their pointwise products, both the representation power and the quality of the function transfer can be improved significantly. Our modification, while computationally simple, allows us to achieve higher transfer accuracy while keeping the size of the basis and the functional map fixed. We also analyze the computational complexity of optimally representing functions through linear combinations of products in a given basis and prove NP-completeness in some general cases. Finally, we argue that the use of function products can have a wide-reaching effect in extending the power of functional maps in a variety of applications, in particular by enabling the transfer of highfrequency functions without changing the representation size or complexity.
Interactive Generation of Time-evolving, Snow-Covered Landscapes with Avalanches
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Cordonnier, Guillaume; Ecormier, Pierre; Galin, Eric; Gain, James; Benes, Bedrich; Cani, Marie-Paule; Gutierrez, Diego and Sheffer, Alla
We introduce a novel method for interactive generation of visually consistent, snow-covered landscapes and provide control of their dynamic evolution over time. Our main contribution is the real-time phenomenological simulation of avalanches and other user-guided events, such as tracks left by Nordic skiing, which can be applied to interactively sculpt the landscape. The terrain is modeled as a height field with additional layers for stable, compacted, unstable, and powdery snow, which behave in combination as a semi-viscous fluid. We incorporate the impact of several phenomena, including sunlight, temperature, prevailing wind direction, and skiing activities. The snow evolution includes snow-melt and snow-drift, which a ect stability of the snow mass and the probability of avalanches. A user can shape landscapes and their evolution either with a variety of interactive brushes, or by prescribing events along a winter season time-line. Our optimized GPU-implementation allows interactive updates of snow type and depth across a large (10 10km) terrain, including real-time avalanches, making this suitable for visual assets in computer games. We evaluate our method through perceptual comparison against exiting methods and real snow-depth data.
Motion Sickness Simulation Based on Sensorimotor Control
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Hu, Chen-Hui; Lin, Wen-Chieh; Gutierrez, Diego and Sheffer, Alla
Sensorimotor control is an essential mechanism for human motions, from involuntary reflex actions to intentional motor skill learning, such as walking, jumping, and swimming. Humans perform various motions according to different task goals and physiological sensory perception; however, most existing computational approaches for motion simulation and generation rarely consider the effects of human perception. The assumption of perfect perception (i.e., no sensory errors) of existing approaches restricts the generated motion types and makes dynamical reactions less realistic. We propose a general framework for sensorimotor control, integrating a balance controller and a vestibular model, to generate perception-aware motions. By exploiting simulated perception, more natural responses that are closer to human reactions can be generated. For example, motion sickness caused by the impairments in the function of the vestibular system induces postural instability and body sway. Our approach generates physically correct motions and reasonable reactions to external stimuli since the spatial orientation estimation by the vestibular system is essential to preserve balance. We evaluate our framework by demonstrating standing balance on a rotational platform with different angular speeds and duration. The generated motions show that either faster angular speeds or longer rotational duration cause more severe motion sickness. Our results demonstrate that sensorimotor control, integrating human perception and physically-based control, offers considerable potential for providing more human-like behaviors, especially for perceptual illusions of human beings, including visual, proprioceptive, and tactile sensations.
A New Microflake Model With Microscopic Self-shadowing for Accurate Volume Downsampling
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Loubet, Guillaume; Neyret, Fabrice; Gutierrez, Diego and Sheffer, Alla
Naive linear methods for downsampling high-resolution microflake volumes often produce inaccurate appearance, especially when input voxels are very opaque. Preserving correct appearance at all resolutions requires taking into account maskingshadowing effects that occur between and inside dense input voxels. We introduce a new microflake model whose additional parameters characterize self-shadowing effects at a microscopic scale. We provide an anisotropic self-shadowing function and microflake distributions for which the scattering coefficients and the phase functions of our model have closed-form expressions. We use this model in a new downsampling approach in which scattering parameters are computed from local estimations of self-shadowing probabilities in the input volume. Unlike previous work, our method handles datasets with spatially varying scattering parameters, semi-transparent volumes and datasets with intricate silhouettes. We show that our method generates LoDs with correct transparency and consistent appearance through scales for a wide range of challenging datasets, allowing for huge memory savings and efficient distant rendering without loss of quality.
PCPNet: Learning Local Shape Properties from Raw Point Clouds
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Guerrero, Paul; Kleiman, Yanir; Ovsjanikov, Maks; Mitra, Niloy J.; Gutierrez, Diego and Sheffer, Alla
In this paper, we propose PCPNET, a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape classification or semantic labeling, we suggest a patch-based learning method, in which a series of local patches at multiple scales around each point is encoded in a structured manner. Our approach is especially well-adapted for estimating local shape properties such as normals (both unoriented and oriented) and curvature from raw point clouds in the presence of strong noise and multi-scale features. Our main contributions include both a novel multi-scale variant of the recently proposed PointNet architecture with emphasis on local shape information, and a series of novel applications in which we demonstrate how learning from training data arising from well-structured triangle meshes, and applying the trained model to noisy point clouds can produce superior results compared to specialized state-of-the-art techniques. Finally, we demonstrate the utility of our approach in the context of shape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.
A Physically Consistent Implicit Viscosity Solver for SPH Fluids
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Weiler, Marcel; Koschier, Dan; Brand, Magnus; Bender, Jan; Gutierrez, Diego and Sheffer, Alla
In this paper, we present a novel physically consistent implicit solver for the simulation of highly viscous fluids using the Smoothed Particle Hydrodynamics (SPH) formalism. Our method is the result of a theoretical and practical in-depth analysis of the most recent implicit SPH solvers for viscous materials. Based on our findings, we developed a list of requirements that are vital to produce a realistic motion of a viscous fluid. These essential requirements include momentum conservation, a physically meaningful behavior under temporal and spatial refinement, the absence of ghost forces induced by spurious viscosities and the ability to reproduce complex physical effects that can be observed in nature. On the basis of several theoretical analyses, quantitative academic comparisons and complex visual experiments we show that none of the recent approaches is able to satisfy all requirements. In contrast, our proposed method meets all demands and therefore produces realistic animations in highly complex scenarios. We demonstrate that our solver outperforms former approaches in terms of physical accuracy and memory consumption while it is comparable in terms of computational performance. In addition to the implicit viscosity solver, we present a method to simulate melting objects. Therefore, we generalize the viscosity model to a spatially varying viscosity field and provide an SPH discretization of the heat equation.
PointProNets: Consolidation of Point Clouds with Convolutional Neural Networks
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Roveri, Riccardo; Öztireli, A. Cengiz; Pandele, Ioana; Gross, Markus; Gutierrez, Diego and Sheffer, Alla
With the widespread use of 3D acquisition devices, there is an increasing need of consolidating captured noisy and sparse point cloud data for accurate representation of the underlying structures. There are numerous algorithms that rely on a variety of assumptions such as local smoothness to tackle this ill-posed problem. However, such priors lead to loss of important features and geometric detail. Instead, we propose a novel data-driven approach for point cloud consolidation via a convolutional neural network based technique. Our method takes a sparse and noisy point cloud as input, and produces a dense point cloud accurately representing the underlying surface by resolving ambiguities in geometry. The resulting point set can then be used to reconstruct accurate manifold surfaces and estimate surface properties. To achieve this, we propose a generative neural network architecture that can input and output point clouds, unlocking a powerful set of tools from the deep learning literature. We use this architecture to apply convolutional neural networks to local patches of geometry for high quality and efficient point cloud consolidation. This results in significantly more accurate surfaces, as we illustrate with a diversity of examples and comparisons to the state-of-the-art.

Browse

Browsing 37-Issue 2 by Subject "Computing methodologies"

Results Per Page

Sort Options