38-Issue 2
Permanent URI for this collection
Browse
Browsing 38-Issue 2 by Issue Date
Now showing 1 - 20 of 38
Results Per Page
Sort Options
Item A Subspace Method for Fast Locally Injective Harmonic Mapping(The Eurographics Association and John Wiley & Sons Ltd., 2019) Hefetz, Eden Fedida; Chien, Edward; Weber, Ofir; Alliez, Pierre and Pellacini, FabioWe present a fast algorithm for low-distortion locally injective harmonic mappings of genus 0 triangle meshes with and without cone singularities. The algorithm consists of two portions, a linear subspace analysis and construction, and a nonlinear nonconvex optimization for determination of a mapping within the reduced subspace. The subspace is the space of solutions to the Harmonic Global Parametrization (HGP) linear system [BCW17], and only vertex positions near cones are utilized, decoupling the variable count from the mesh density. A key insight shows how to construct the linear subspace at a cost comparable to that of a linear solve, extracting a very small set of elements from the inverse of the matrix without explicitly calculating it. With a variable count on the order of the number of cones, a tangential alternating projection method [HCW17] and a subsequent Newton optimization [CW17] are used to quickly find a low-distortion locally injective mapping. This mapping determination is typically much faster than the subspace construction. Experiments demonstrating its speed and efficacy are shown, and we find it to be an order of magnitude faster than HGP and other alternatives.Item Neural BTF Compression and Interpolation(The Eurographics Association and John Wiley & Sons Ltd., 2019) Rainer, Gilles; Jakob, Wenzel; Ghosh, Abhijeet; Weyrich, Tim; Alliez, Pierre and Pellacini, FabioThe Bidirectional Texture Function (BTF) is a data-driven solution to render materials with complex appearance. A typical capture contains tens of thousands of images of a material sample under varying viewing and lighting conditions.While capable of faithfully recording complex light interactions in the material, the main drawback is the massive memory requirement, both for storing and rendering, making effective compression of BTF data a critical component in practical applications. Common compression schemes used in practice are based on matrix factorization techniques, which preserve the discrete format of the original dataset. While this approach generalizes well to different materials, rendering with the compressed dataset still relies on interpolating between the closest samples. Depending on the material and the angular resolution of the BTF, this can lead to blurring and ghosting artefacts. An alternative approach uses analytic model fitting to approximate the BTF data, using continuous functions that naturally interpolate well, but whose expressive range is often not wide enough to faithfully recreate materials with complex non-local lighting effects (subsurface scattering, inter-reflections, shadowing and masking...). In light of these observations, we propose a neural network-based BTF representation inspired by autoencoders: our encoder compresses each texel to a small set of latent coefficients, while our decoder additionally takes in a light and view direction and outputs a single RGB vector at a time. This allows us to continuously query reflectance values in the light and view hemispheres, eliminating the need for linear interpolation between discrete samples. We train our architecture on fabric BTFs with a challenging appearance and compare to standard PCA as a baseline. We achieve competitive compression ratios and high-quality interpolation/extrapolation without blurring or ghosting artifacts.Item EUROGRAPHICS 2019: CGF 38-2 Frontmatter(The Eurographics Association and John Wiley & Sons Ltd., 2019) Alliez, Pierre; Pellacini, Fabio; Alliez, Pierre and Pellacini, Fabio-Item Procedural Tectonic Planets(The Eurographics Association and John Wiley & Sons Ltd., 2019) Cortial, Yann; Peytavie, Adrien; Galin, Eric; Guérin, Eric; Alliez, Pierre and Pellacini, FabioWe present a procedural method for authoring synthetic tectonic planets. Instead of relying on computationally demanding physically-based simulations, we capture the fundamental phenomena into a procedural method that faithfully reproduces largescale planetary features generated by the movement and collision of the tectonic plates. We approximate complex phenomena such as plate subduction or collisions to deform the lithosphere, including the continental and oceanic crusts. The user can control the movement of the plates, which dynamically evolve and generate a variety of landforms such as continents, oceanic ridges, large scale mountain ranges or island arcs. Finally, we amplify the large-scale planet model with either procedurallydefined or real-world elevation data to synthesize coherent detailed reliefs. Our method allows the user to control the evolution of an entire planet interactively, and to trigger specific events such as catastrophic plate rifting.Item Practical Person-Specific Eye Rigging(The Eurographics Association and John Wiley & Sons Ltd., 2019) Bérard, Pascal; Bradley, Derek; Gross, Markus; Beeler, Thabo; Alliez, Pierre and Pellacini, FabioWe present a novel parametric eye rig for eye animation, including a new multi-view imaging system that can reconstruct eye poses at submillimeter accuracy to which we fit our new rig. This allows us to accurately estimate person-specific eyeball shape, rotation center, interocular distance, visual axis, and other rig parameters resulting in an animation-ready eye rig. We demonstrate the importance of several aspects of eye modeling that are often overlooked, for example that the visual axis is not identical to the optical axis, that it is important to model rotation about the optical axis, and that the rotation center of the eye should be measured accurately for each person. Since accurate rig fitting requires hand annotation of multi-view imagery for several eye gazes, we additionally propose a more user-friendly ''lightweight'' fitting approach, which leverages an average rig created from several pre-captured accurate rigs. Our lightweight rig fitting method allows for the estimation of eyeball shape and eyeball position given only a single pose with a known look-at point (e.g. looking into a camera) and few manual annotations.Item Dynamic Visibility-Driven Molecular Surfaces(The Eurographics Association and John Wiley & Sons Ltd., 2019) Bruckner, Stefan; Alliez, Pierre and Pellacini, FabioMolecular surface representations are an important tool for the visual analysis of molecular structure and function. In this paper, we present a novel method for the visualization of dynamic molecular surfaces based on the Gaussian model. In contrast to previous approaches, our technique does not rely on the construction of intermediate representations such as grids or triangulated surfaces. Instead, it operates entirely in image space, which enables us to exploit visibility information to efficiently skip unnecessary computations. With this visibility-driven approach, we can visualize dynamic high-quality surfaces for molecules consisting of millions of atoms. Our approach requires no preprocessing, allows for the interactive adjustment of all properties and parameters, and is significantly faster than previous approaches, while providing superior quality.Item Character Navigation in Dynamic Environments Based on Optical Flow(The Eurographics Association and John Wiley & Sons Ltd., 2019) López, Axel; Francois, Chaumette; Marchand, Eric; Pettré, Julien; Alliez, Pierre and Pellacini, FabioSteering and navigation are important components of character animation systems to enable them to autonomously move in their environment. In this work, we propose a synthetic vision model that uses visual features to steer agents through dynamic environments. Our agents perceive optical flow resulting from their relative motion with the objects of the environment. The optical flow is then segmented and processed to extract visual features such as the focus of expansion and time-to-collision. Then, we establish the relations between these visual features and the agent motion, and use them to design a set of control functions which allow characters to perform object-dependent tasks, such as following, avoiding and reaching. Control functions are then combined to let characters perform more complex navigation tasks in dynamic environments, such as reaching a goal while avoiding multiple obstacles. Agent's motion is achieved by local minimization of these functions. We demonstrate the efficiency of our approach through a number of scenarios. Our work sets the basis for building a character animation system which imitates human sensorimotor actions. It opens new perspectives to achieve realistic simulation of human characters taking into account perceptual factors, such as the lighting conditions of the environment.Item Deep HDR Video from Sequences with Alternating Exposures(The Eurographics Association and John Wiley & Sons Ltd., 2019) Kalantari, Nima Khademi; Ramamoorthi, Ravi; Alliez, Pierre and Pellacini, FabioA practical way to generate a high dynamic range (HDR) video using off-the-shelf cameras is to capture a sequence with alternating exposures and reconstruct the missing content at each frame. Unfortunately, existing approaches are typically slow and are not able to handle challenging cases. In this paper, we propose a learning-based approach to address this difficult problem. To do this, we use two sequential convolutional neural networks (CNN) to model the entire HDR video reconstruction process. In the first step, we align the neighboring frames to the current frame by estimating the flows between them using a network, which is specifically designed for this application. We then combine the aligned and current images using another CNN to produce the final HDR frame. We perform an end-to-end training by minimizing the error between the reconstructed and ground truth HDR images on a set of training scenes. We produce our training data synthetically from existing HDR video datasets and simulate the imperfections of standard digital cameras using a simple approach. Experimental results demonstrate that our approach produces high-quality HDR videos and is an order of magnitude faster than the state-of-the-art techniques for sequences with two and three alternating exposures.Item Exact Constraint Satisfaction for Truly Seamless Parametrization(The Eurographics Association and John Wiley & Sons Ltd., 2019) Mandad, Manish; Campen, Marcel; Alliez, Pierre and Pellacini, FabioIn the field of global surface parametrization a recent focus has been on so-called seamless parametrization. This term refers to parametrization approaches which, while using an atlas of charts to enable the handling of surfaces of arbitrary topology, relate the parametrization across the cuts between charts via transition functions from special classes of transformations. This effectively makes the cuts invisible to applications which are invariant to these specific transformations in some sense. In actual implementations of these parametrization approaches, however, these restrictions are obeyed only approximately; errors stem from the tolerances of numerical solvers employed and, ultimately, from the limited accuracy of floating point arithmetic. In practice, robustness issues arise from these flaws in the seamlessness of a parametrization, no matter how small. We present a robust global algorithm that turns a given approximately seamless parametrization into an exactly seamless one - that still is representable by standard floating point numbers. It supports common practically relevant additional constraints regarding boundary and feature curve alignment or isocurve connectivity, and ensures that these are likewise fulfilled exactly. This allows subsequent algorithms to operate robustly on the resulting truly seamless parametrization. We believe that the core of our method will furthermore be of benefit in a broader range of applications involving linearly constrained numerical optimization.Item Latent-space Dynamics for Reduced Deformable Simulation(The Eurographics Association and John Wiley & Sons Ltd., 2019) Fulton, Lawson; Modi, Vismay; Duvenaud, David; Levin, David I. W.; Jacobson, Alec; Alliez, Pierre and Pellacini, FabioWe propose the first reduced model simulation framework for deformable solid dynamics using autoencoder neural networks. We provide a data-driven approach to generating nonlinear reduced spaces for deformation dynamics. In contrast to previous methods using machine learning which accelerate simulation by approximating the time-stepping function, we solve the true equations of motion in the latent-space using a variational formulation of implicit integration. Our approach produces drastically smaller reduced spaces than conventional linear model reduction, improving performance and robustness. Furthermore, our method works well with existing force-approximation cubature methods.Item StyleBlit: Fast Example-Based Stylization with Local Guidance(The Eurographics Association and John Wiley & Sons Ltd., 2019) Sýkora, Daniel; Jamriška, Ondrej; Texler, Ondrej; Fišer, Jakub; Lukác, Mike; Lu, Jingwan; Shechtman, Eli; Alliez, Pierre and Pellacini, FabioWe present StyleBlit-an efficient example-based style transfer algorithm that can deliver high-quality stylized renderings in real-time on a single-core CPU. Our technique is especially suitable for style transfer applications that use local guidance - descriptive guiding channels containing large spatial variations. Local guidance encourages transfer of content from the source exemplar to the target image in a semantically meaningful way. Typical local guidance includes, e.g., normal values, texture coordinates or a displacement field. Contrary to previous style transfer techniques, our approach does not involve any computationally expensive optimization. We demonstrate that when local guidance is used, optimization-based techniques converge to solutions that can be well approximated by simple pixel-level operations. Inspired by this observation, we designed an algorithm that produces results visually similar to, if not better than, the state-of-the-art, and is several orders of magnitude faster. Our approach is suitable for scenarios with low computational budget such as games and mobile applications.Item Design and Automated Generation of Japanese Picture Puzzles(The Eurographics Association and John Wiley & Sons Ltd., 2019) Kerkhof, Mees van de; Jong, Tim de; Parment, Raphael; Löffler, Maarten; Vaxman, Amir; van Kreveld, Marc; Alliez, Pierre and Pellacini, FabioWe introduce the generalized nonogram, an extension of the well-known nonogram or Japanese picture puzzle. It is not based on a regular square grid but on a subdivision (arrangement) with differently shaped cells, bounded by straight lines or curves. To generate a good, clear puzzle from a filled line drawing, the arrangement that is formed for the puzzle must meet a number of criteria. Some of these relate to the puzzle and some to the geometry. We give an overview of these criteria and show that a puzzle can be generated by an optimization method like simulated annealing. Experimentally, we analyze the convergence of the method and the remaining penalty score on several input pictures along with various other design options.Item Computational Design of Steady 3D Dissection Puzzles(The Eurographics Association and John Wiley & Sons Ltd., 2019) Tang, Keke; Song, Peng; Wang, Xiaofei; Deng, Bailin; Fu, Chi-Wing; Liu, Ligang; Alliez, Pierre and Pellacini, FabioDissection puzzles require assembling a common set of pieces into multiple distinct forms. Existing works focus on creating 2D dissection puzzles that form primitive or naturalistic shapes. Unlike 2D dissection puzzles that could be supported on a tabletop surface, 3D dissection puzzles are preferable to be steady by themselves for each assembly form. In this work, we aim at computationally designing steady 3D dissection puzzles. We address this challenging problem with three key contributions. First, we take two voxelized shapes as inputs and dissect them into a common set of puzzle pieces, during which we allow slightly modifying the input shapes, preferably on their internal volume, to preserve the external appearance. Second, we formulate a formal model of generalized interlocking for connecting pieces into a steady assembly using both their geometric arrangements and friction. Third, we modify the geometry of each dissected puzzle piece based on the formal model such that each assembly form is steady accordingly. We demonstrate the effectiveness of our approach on a wide variety of shapes, compare it with the state-of-the-art on 2D and 3D examples, and fabricate some of our designed puzzles to validate their steadiness.Item Accurate Synthesis of Multi-Class Disk Distributions(The Eurographics Association and John Wiley & Sons Ltd., 2019) Ecormier-Nocca, Pierre; Memari, Pooran; Gain, James; Cani, Marie-Paule; Alliez, Pierre and Pellacini, FabioWhile analysing and synthesising 2D distributions of points has been applied both to the generation of textures with discrete elements and for populating virtual worlds with 3D objects, the results are often inaccurate since the spatial extent of objects cannot be expressed.We introduce three improvements enabling the synthesis of more general distributions of elements. First, we extend continuous pair correlation function (PCF) algorithms to multi-class distributions using a dependency graph, thereby capturing interrelationships between distinct categories of objects. Second, we introduce a new normalised metric for disks, which makes the method applicable to both point and possibly overlapping disk distributions. The metric is specifically designed to distinguish perceptually salient features, such as disjoint, tangent, overlapping, or nested disks. Finally, we pay particular attention to convergence of the mean PCF as well as the validity of individual PCFs, by taking into consideration the variance of the input. Our results demonstrate that this framework can capture and reproduce real-life distributions of elements representing a variety of complex semi-structured patterns, from the interaction between trees and the understorey in a forest to droplets of water. More generally, it applies to any category of 2D object whose shape is better represented by bounding circles than points.Item Generating Color Scribble Images using Multi-layered Monochromatic Strokes Dithering(The Eurographics Association and John Wiley & Sons Ltd., 2019) Lo, Yi-Hsiang; Lee, Ruen-Rone; Chu, Hung-Kuo; Alliez, Pierre and Pellacini, FabioColor scribbling is a unique form of illustration where artists use compact, overlapping, and monochromatic scribbles at microscopic scale to create astonishing colorful images at macroscopic scale. The creation process is skill-demanded and time-consuming, which typically involves drawing monochromatic scribbles layer-by-layer to depict true-color subjects using a limited color palette delicately. In this work, we present a novel computational framework for automatic generation of color scribble images from arbitrary raster images. The core contribution of our work lies in a novel color dithering model tailormade for synthesizing a smooth color appearance using multiple layers of overlapped monochromatic strokes. Specifically, our system reconstructs the appearance of the input image by (i) generating layers of monochromatic scribbles based on a limited color palette derived from input image, and (ii) optimizing the drawing sequence among layers to minimize the visual color dissimilarity between dithered image and original image as well as the color banding artifacts. We demonstrate the effectiveness and robustness of our algorithm with various convincing results synthesized from a variety of input images with different stroke patterns. The experimental study further shows that our approach faithfully captures the scribble style and the color presentation at respectively microscopic and macroscopic scales, which is otherwise difficult for state-of-the-art methods.Item Learning a Generative Model for Multi-Step Human-Object Interactions from Videos(The Eurographics Association and John Wiley & Sons Ltd., 2019) Wang, He; Pirk, Sören; Yumer, Ersin; Kim, Vladimir; Sener, Ozan; Sridhar, Srinath; Guibas, Leonidas; Alliez, Pierre and Pellacini, FabioCreating dynamic virtual environments consisting of humans interacting with objects is a fundamental problem in computer graphics. While it is well-accepted that agent interactions play an essential role in synthesizing such scenes, most extant techniques exclusively focus on static scenes, leaving the dynamic component out. In this paper, we present a generative model to synthesize plausible multi-step dynamic human-object interactions. Generating multi-step interactions is challenging since the space of such interactions is exponential in the number of objects, activities, and time steps. We propose to handle this combinatorial complexity by learning a lower dimensional space of plausible human-object interactions. We use action plots to represent interactions as a sequence of discrete actions along with the participating objects and their states. To build action plots, we present an automatic method that uses state-of-the-art computer vision techniques on RGB videos in order to detect individual objects and their states, extract the involved hands, and recognize the actions performed. The action plots are built from observing videos of everyday activities and are used to train a generative model based on a Recurrent Neural Network (RNN). The network learns the causal dependencies and constraints between individual actions and can be used to generate novel and diverse multi-step human-object interactions. Our representation and generative model allows new capabilities in a variety of applications such as interaction prediction, animation synthesis, and motion planning for a real robotic agent.Item Learning to Importance Sample in Primary Sample Space(The Eurographics Association and John Wiley & Sons Ltd., 2019) Zheng, Quan; Zwicker, Matthias; Alliez, Pierre and Pellacini, FabioImportance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. We propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. Our approach considers an existing Monte Carlo rendering algorithm as a black box. During a scene-dependent training phase, we learn to generate samples with a desired density in the primary sample space of the renderer using maximum likelihood estimation. We leverage a recent neural network architecture that was designed to represent real-valued non-volume preserving (''Real NVP'') transformations in high dimensional spaces. We use Real NVP to non-linearly warp primary sample space and obtain desired densities. In addition, Real NVP efficiently computes the determinant of the Jacobian of the warp, which is required to implement the change of integration variables implied by the warp. A main advantage of our approach is that it is agnostic of underlying light transport effects, and can be combined with an existing rendering technique by treating it as a black box. We show that our approach leads to effective variance reduction in several practical scenarios.Item Gradient Outlier Removal for Gradient-Domain Path Tracing(The Eurographics Association and John Wiley & Sons Ltd., 2019) Ha, Saerom; Oh, Sojin; Back, Jonghee; Yoon, Sung-Eui; Moon, Bochang; Alliez, Pierre and Pellacini, FabioWe present a new outlier removal technique for a gradient-domain path tracing (G-PT) that computes image gradients as well as colors. Our approach rejects gradient outliers whose estimated errors are much higher than those of the other gradients for improving reconstruction quality for the G-PT. We formulate our outlier removal problem as a least trimmed squares optimization, which employs only a subset of gradients so that a final image can be reconstructed without including the gradient outliers. In addition, we design this outlier removal process so that the chosen subset of gradients maintains connectivity through gradients between pixels, preventing pixels from being isolated. Lastly, the optimal number of inlier gradients is estimated to minimize our reconstruction error. We have demonstrated that our reconstruction with robustly rejecting gradient outliers produces visually and numerically improved results, compared to the previous screened Poisson reconstruction that uses all the gradients.Item A CNN-based Flow Correction Method for Fast Preview(The Eurographics Association and John Wiley & Sons Ltd., 2019) Xiao, Xiangyun; Wang, Hui; Yang, Xubo; Alliez, Pierre and Pellacini, FabioEulerian-based smoke simulations are sensitive to the initial parameters and grid resolutions. Due to the numerical dissipation on different levels of the grid and the nonlinearity of the governing equations, the differences in simulation resolutions will result in different results. This makes it challenging for artists to preview the animation results based on low-resolution simulations. In this paper, we propose a learning-based flow correction method for fast previewing based on low-resolution smoke simulations. The main components of our approach lie in a deep convolutional neural network, a grid-layer feature vector and a special loss function. We provide a novel matching model to represent the relationship between low-resolution and high-resolution smoke simulations and correct the overall shape of a low-resolution simulation to closely follow the shape of a high-resolution down-sampled version. We introduce the grid-layer concept to effectively represent the 3D fluid shape, which can also reduce the input and output dimensions. We design a special loss function for the fluid divergence-free constraint in the neural network training process. We have demonstrated the efficacy and the generality of our approach by simulating a diversity of animations deviating from the original training set. In addition, we have integrated our approach into an existing fluid simulation framework to showcase its wide applications.Item Deep Video-Based Performance Cloning(The Eurographics Association and John Wiley & Sons Ltd., 2019) Aberman, Kfir; Shi, Mingyi; Liao, Jing; Lischinski, Dani; Chen, Baoquan; Cohen-Or, Daniel; Alliez, Pierre and Pellacini, FabioWe present a new video-based performance cloning technique. After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances. All of the training data and the driving performances are provided as ordinary video segments, without motion capture or depth information. Our generative model is realized as a deep neural network with two branches, both of which train the same space-time conditional generator, using shared weights. One branch, responsible for learning to generate the appearance of the target actor in various poses, uses paired training data, self-generated from the reference video. The second branch uses unpaired data to improve generation of temporally coherent video renditions of unseen pose sequences. Through data augmentation, our network is able to synthesize images of the target actor in poses never captured by the reference video. We demonstrate a variety of promising results, where our method is able to generate temporally coherent videos, for challenging scenarios where the reference and driving videos consist of very different dance performances.