40-Issue 2

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633016

Browse

Now showing 1 - 20 of 38

Adversarial Single-Image SVBRDF Estimation with Hybrid Training
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Zhou, Xilong; Kalantari, Nima Khademi; Mitra, Niloy and Viola, Ivan
In this paper, we propose a deep learning approach for estimating the spatially-varying BRDFs (SVBRDF) from a single image. Most existing deep learning techniques use pixel-wise loss functions which limits the flexibility of the networks in handling this highly unconstrained problem. Moreover, since obtaining ground truth SVBRDF parameters is difficult, most methods typically train their networks on synthetic images and, therefore, do not effectively generalize to real examples. To avoid these limitations, we propose an adversarial framework to handle this application. Specifically, we estimate the material properties using an encoder-decoder convolutional neural network (CNN) and train it through a series of discriminators that distinguish the output of the network from ground truth. To address the gap in data distribution of synthetic and real images, we train our network on both synthetic and real examples. Specifically, we propose a strategy to train our network on pairs of real images of the same object with different lighting. We demonstrate that our approach is able to handle a variety of cases better than the state-of-the-art methods.
Automatic Surface Segmentation for Seamless Fabrication Using 4-axis Milling Machines
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Nuvoli, Stefano; Tola, Alessandro; Muntoni, Alessandro; Pietroni, Nico; Gobbetti, Enrico; Scateni, Riccardo; Mitra, Niloy and Viola, Ivan
We introduce a novel geometry-processing pipeline to guide the fabrication of complex shapes from a single block of material using 4-axis CNC milling machines. This setup extends classical 3-axis CNC machining with an extra degree of freedom to rotate the object around a fixed axis. The first step of our pipeline identifies the rotation axis that maximizes the overall fabrication accuracy. Then we identify two height-field regions at the rotation axis's extremes used to secure the block on the rotation tool. We segment the remaining portion of the mesh into a set of height-fields whose principal directions are orthogonal to the rotation axis. The segmentation balances the approximation quality, the boundary smoothness, and the total number of patches. Additionally, the segmentation process takes into account the object's geometric features, as well as saliency information. The output is a set of meshes ready to be processed by off-the-shelf software for the 3-axis tool-path generation. We present several results to demonstrate the quality and efficiency of our approach to a range of inputs
Coherent Mark-based Stylization of 3D Scenes at the Compositing Stage
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Garcia, Maxime; Vergne, Romain; Farhat, Mohamed-Amine; Bénard, Pierre; Noûs, Camille; Thollot, Joëlle; Mitra, Niloy and Viola, Ivan
We present a novel temporally coherent stylized rendering technique working entirely at the compositing stage. We first generate a distribution of 3D anchor points using an implicit grid based on the local object positions stored in a G-buffer, hence following object motion. We then draw splats in screen space anchored to these points so as to be motion coherent. To increase the perceived flatness of the style, we adjust the anchor points density using a fractalization mechanism. Sudden changes are prevented by controlling the anchor points opacity and introducing a new order-independent blending function. We demonstrate the versatility of our method by showing a large variety of styles thanks to the freedom offered by the splats content and their attributes that can be controlled by any G-buffer.
Correlation-Aware Multiple Importance Sampling for Bidirectional Rendering Algorithms
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Grittmann, Pascal; Georgiev, Iliyan; Slusallek, Philipp; Mitra, Niloy and Viola, Ivan
Combining diverse sampling techniques via multiple importance sampling (MIS) is key to achieving robustness in modern Monte Carlo light transport simulation. Many such methods additionally employ correlated path sampling to boost efficiency. Photon mapping, bidirectional path tracing, and path-reuse algorithms construct sets of paths that share a common prefix. This correlation is ignored by classical MIS heuristics, which can result in poor technique combination and noisy images.We propose a practical and robust solution to that problem. Our idea is to incorporate correlation knowledge into the balance heuristic, based on known path densities that are already required for MIS. This correlation-aware heuristic can achieve considerably lower error than the balance heuristic, while avoiding computational and memory overhead.
Cyclostationary Gaussian Noise: Theory and Synthesis
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Lutz, Nicolas; Sauvage, Basile; Dischler, Jean-Michel; Mitra, Niloy and Viola, Ivan
Stationary Gaussian processes have been used for decades in the context of procedural noises to model and synthesize textures with no spatial organization. In this paper we investigate cyclostationary Gaussian processes, whose statistics are repeated periodically. It enables the modeling of noises having periodic spatial variations, which we call "cyclostationary Gaussian noises". We adapt to the cyclostationary context several stationary noises along with their synthesis algorithms: spot noise, Gabor noise, local random-phase noise, high-performance noise, and phasor noise. We exhibit real-time synthesis of a variety of visual patterns having periodic spatial variations.
Enabling Viewpoint Learning through Dynamic Label Generation
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Schelling, Michael; Hermosilla, Pedro; Vázquez, Pere-Pau; Ropinski, Timo; Mitra, Niloy and Viola, Ivan
Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed-form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end-to-end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state-of-the-art (SOTA) viewpoint quality evaluation. Code and training data is available at https://github.com/schellmi42/viewpoint_learning, which is to our knowledge the biggest viewpoint quality dataset available.
Hierarchical Raster Occlusion Culling
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Lee, Gi Beom; Jeong, Moonsoo; Seok, Yechan; Lee, Sungkil; Mitra, Niloy and Viola, Ivan
This paper presents a scalable online occlusion culling algorithm, which significantly improves the previous raster occlusion culling using object-level bounding volume hierarchy. Given occluders found with temporal coherence, we find and rasterize coarse groups of potential occludees in the hierarchy. Within the rasterized bounds, per-pixel ray casting tests fine-grained visibilities of every individual occludees. We further propose acceleration techniques including the read-back of counters for tightly-packed multidrawing and occluder filtering. Our solution requires only constant draw calls for batch occlusion tests, while avoiding costly iteration for hierarchy traversal. Our experiments prove our solution outperforms the existing solutions in terms of scalability, culling efficiency, and occlusion-query performance.
Higher Dimensional Graphics: Conceiving Worlds in Four Spatial Dimensions and Beyond
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Cavallo, Marco; Mitra, Niloy and Viola, Ivan
While the interpretation of high-dimensional datasets has become a necessity in most industries, the spatial visualization of higher-dimensional geometry has mostly remained a niche research topic for mathematicians and physicists. Intermittent contributions to this field date back more than a century, and have had a non-negligible influence on contemporary art and philosophy. However, most contributions have focused on the understanding of specific mathematical shapes, with few concrete applications. In this work, we attempt to revive the community's interest in visualizing higher dimensional geometry by shifting the focus from the visualization of abstract shapes to the design of a broader hyper-universe concept, wherein 3D and 4D objects can coexist and interact with each other. Specifically, we discuss the content definition, authoring patterns, and technical implementations associated with the process of extending standard 3D applications as to support 4D mechanics. We operationalize our ideas through the introduction of a new hybrid 3D/4D videogame called Across Dimensions, which we developed in Unity3D through the integration of our own 4D plugin.
Honey, I Shrunk the Domain: Frequency-aware Force Field Reduction for Efficient Fluids Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Tang, Jingwei; Azevedo, Vinicius C.; Cordonnier, Guillaume; Solenthaler, Barbara; Mitra, Niloy and Viola, Ivan
Fluid control often uses optimization of control forces that are added to a simulation at each time step, such that the final animation matches a single or multiple target density keyframes provided by an artist. The optimization problem is strongly under-constrained with a high-dimensional parameter space, and finding optimal solutions is challenging, especially for higher resolution simulations. In this paper, we propose two novel ideas that jointly tackle the lack of constraints and high dimensionality of the parameter space. We first consider the fact that optimized forces are allowed to have divergent modes during the optimization process. These divergent modes are not entirely projected out by the pressure solver step, manifesting as unphysical smoke sources that are explored by the optimizer to match a desired target. Thus, we reduce the space of the possible forces to the family of strictly divergence-free velocity fields, by optimizing directly for a vector potential. We synergistically combine this with a smoothness regularization based on a spectral decomposition of control force fields. Our method enforces lower frequencies of the force fields to be optimized first by filtering force frequencies in the Fourier domain. The mask-growing strategy is inspired by Kolmogorov's theory about scales of turbulence. We demonstrate improved results for 2D and 3D fluid control especially in higher-resolution settings, while eliminating the need for manual parameter tuning. We showcase various applications of our method, where the user effectively creates or edits smoke simulations.
Interactive Photo Editing on Smartphones via Intrinsic Decomposition
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Shekhar, Sumit; Reimann, Max; Mayer, Maximilian; Semmo, Amir; Pasewaldt, Sebastian; Döllner, Jürgen; Trapp, Matthias; Mitra, Niloy and Viola, Ivan
Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPUbased visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.
Layout Embedding via Combinatorial Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Born, Janis; Schmidt, Patrick; Kobbelt, Leif; Mitra, Niloy and Viola, Ivan
We consider the problem of injectively embedding a given graph connectivity (a layout) into a target surface. Starting from prescribed positions of layout vertices, the task is to embed all layout edges as intersection-free paths on the surface. Besides merely geometric choices (the shape of paths) this problem is especially challenging due to its topological degrees of freedom (how to route paths around layout vertices). The problem is typically addressed through a sequence of shortest path insertions, ordered by a greedy heuristic. Such insertion sequences are not guaranteed to be optimal: Early path insertions can potentially force later paths into unexpected homotopy classes. We show how common greedy methods can easily produce embeddings of dramatically bad quality, rendering such methods unsuitable for automatic processing pipelines. Instead, we strive to find the optimal order of insertions, i.e. the one that minimizes the total path length of the embedding. We demonstrate that, despite the vast combinatorial solution space, this problem can be effectively solved on simply-connected domains via a custom-tailored branch-and-bound strategy. This enables directly using the resulting embeddings in downstream applications which cannot recover from initializations in a wrong homotopy class. We demonstrate the robustness of our method on a shape dataset by embedding a common template layout per category, and show applications in quad meshing and inter-surface mapping.
Learning and Exploring Motor Skills with Spacetime Bounds
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Ma, Li-Ke; Yang, Zeshi; Tong, Xin; Guo, Baining; Yin, KangKang; Mitra, Niloy and Viola, Ivan
Equipping characters with diverse motor skills is the current bottleneck of physics-based character animation. We propose a Deep Reinforcement Learning (DRL) framework that enables physics-based characters to learn and explore motor skills from reference motions. The key insight is to use loose space-time constraints, termed spacetime bounds, to limit the search space in an early termination fashion. As we only rely on the reference to specify loose spacetime bounds, our learning is more robust with respect to low quality references. Moreover, spacetime bounds are hard constraints that improve learning of challenging motion segments, which can be ignored by imitation-only learning. We compare our method with state-of-the-art tracking-based DRL methods. We also show how to guide style exploration within the proposed framework.
Learning Human Search Behavior from Egocentric Visual Inputs
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Sorokin, Maks; Yu, Wenhao; Ha, Sehoon; Liu, C. Karen; Mitra, Niloy and Viola, Ivan
''Looking for things'' is a mundane but critical task we repeatedly carry on in our daily life. We introduce a method to develop a human character capable of searching for a randomly located target object in a detailed 3D scene using its locomotion capability and egocentric vision perception represented as RGBD images. By depriving the privileged 3D information from the human character, it is forced to move and look around simultaneously to account for the restricted sensing capability, resulting in natural navigation and search behaviors. Our method consists of two components: 1) a search control policy based on an abstract character model, and 2) an online replanning control module for synthesizing detailed kinematic motion based on the trajectories planned by the search policy. We demonstrate that the combined techniques enable the character to effectively find often occluded household items in indoor environments. The same search policy can be applied to different full body characters without the need of retraining. We evaluate our method quantitatively by testing it on randomly generated scenarios. Our work is a first step toward creating intelligent virtual agents with humanlike behaviors driven by onboard sensors, paving the road toward future robotic applications.
Learning Multiple-Scattering Solutions for Sphere-Tracing of Volumetric Subsurface Effects
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Leonard, Ludwic; Höhlein, Kevin; Westermann, Rüdiger; Mitra, Niloy and Viola, Ivan
Accurate subsurface scattering solutions require the integration of optical material properties along many complicated light paths. We present a method that learns a simple geometric approximation of random paths in a homogeneous volume with translucent material. The generated representation allows determining the absorption along the path as well as a direct lighting contribution, which is representative of all scatter events along the path. A sequence of conditional variational auto-encoders (CVAEs) is trained to model the statistical distribution of the photon paths inside a spherical region in the presence of multiple scattering events. A first CVAE learns how to sample the number of scatter events, occurring on a ray path inside the sphere, which effectively determines the probability of this ray to be absorbed. Conditioned on this, a second model predicts the exit position and direction of the light particle. Finally, a third model generates a representative sample of photon position and direction along the path, which is used to approximate the contribution of direct illumination due to in-scattering. To accelerate the tracing of the light path through the volumetric medium toward the solid boundary, we employ a sphere-tracing strategy that considers the light absorption and can perform a statistically accurate next-event estimation. We demonstrate efficient learning using shallow networks of only three layers and no more than 16 nodes. In combination with a GPU shader that evaluates the CVAEs' predictions, performance gains can be demonstrated for a variety of different scenarios. We analyze the approximation error that is introduced by the data-driven scattering simulation and shed light on the major sources of error.
LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Yang, Dongseok; Kim, Doyeon; Lee, Sung-Hee; Mitra, Niloy and Viola, Ivan
With the popularization of games and VR/AR devices, there is a growing need for capturing human motion with a sparse set of tracking data. In this paper, we introduce a deep neural network (DNN) based method for real-time prediction of the lowerbody pose only from the tracking signals of the upper-body joints. Specifically, our Gated Recurrent Unit (GRU)-based recurrent architecture predicts the lower-body pose and feet contact states from a past sequence of tracking signals of the head, hands, and pelvis. A major feature of our method is that the input signal is represented by the velocity of tracking signals. We show that the velocity representation better models the correlation between the upper-body and lower-body motions and increases the robustness against the diverse scales and proportions of the user body than position-orientation representations. In addition, to remove foot-skating and floating artifacts, our network predicts feet contact state, which is used to post-process the lower-body pose with inverse kinematics to preserve the contact. Our network is lightweight so as to run in real-time applications. We show the effectiveness of our method through several quantitative evaluations against other architectures and input representations with respect to wild tracking data obtained from commercial VR devices.
Local Light Alignment for Multi-Scale Shape Depiction
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Mestres, Nolan; Vergne, Romain; Noûs, Camille; Thollot, Joëlle; Mitra, Niloy and Viola, Ivan
Motivated by recent findings in the field of visual perception, we present a novel approach for enhancing shape depiction and perception of surface details. We propose a shading-based technique that relies on locally adjusting the direction of light to account for the different components of materials. Our approach ensures congruence between shape and shading flows, leading to an effective enhancement of the perception of shape and details while impairing neither the lighting nor the appearance of materials. It is formulated in a general way allowing its use for multiple scales enhancement in real-time on the GPU, as well as in global illumination contexts. We also provide artists with fine control over the enhancement at each scale.
MultiResGNet: Approximating Nonlinear Deformation via Multi-Resolution Graphs
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Li, Tianxing; Shi, Rui; Kanai, Takashi; Mitra, Niloy and Viola, Ivan
This paper presents a graph-learning-based, powerfully generalized method for automatically generating nonlinear deformation for characters with an arbitrary number of vertices. Large-scale character datasets with a significant number of poses are normally required for training to learn such automatic generalization tasks. There are two key contributions that enable us to address this challenge while making our network generalized to achieve realistic deformation approximation. First, after the automatic linear-based deformation step, we encode the roughly deformed meshes by constructing graphs where we propose a novel graph feature representation method with three descriptors to represent meshes of arbitrary characters in varying poses. Second, we design a multi-resolution graph network (MultiResGNet) that takes the constructed graphs as input, and end-to-end outputs the offset adjustments of each vertex. By processing multi-resolution graphs, general features can be better extracted, and the network training no longer heavily relies on large amounts of training data. Experimental results show that the proposed method achieves better performance than prior studies in deformation approximation for unseen characters and poses.
A Multiscale Microfacet Model Based on Inverse Bin Mapping
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Atanasov, Asen; Wilkie, Alexander; Koylazov, Vladimir; Krivánek, Jaroslav; Mitra, Niloy and Viola, Ivan
Accurately controllable shading detail is a crucial aspect of realistic appearance modelling. Two fundamental building blocks for this are microfacet BRDFs, which describe the statistical behaviour of infinitely small facets, and normal maps, which provide user-controllable spatio-directional surface features. We analyse the filtering of the combined effect of a microfacet BRDF and a normal map. By partitioning the half-vector domain into bins we show that the filtering problem can be reduced to evaluation of an integral histogram (IH), a generalization of a summed-area table (SAT). Integral histograms are known for their large memory requirements, which are usually proportional to the number of bins. To alleviate this, we introduce Inverse Bin Maps, a specialised form of IH with a memory footprint that is practically independent of the number of bins. Based on these, we present a memory-efficient, production-ready approach for filtering of high resolution normal maps with arbitrary Beckmann flake roughness. In the corner case of specular normal maps (zero, or very small roughness values) our method shows similar convergence rates to the current state of the art, and is also more memory efficient.
Neural Acceleration of Scattering-Aware Color 3D Printing
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Rittig, Tobias; Sumin, Denis; Babaei, Vahid; Didyk, Piotr; Voloboy, Alexey; Wilkie, Alexander; Bickel, Bernd; Myszkowski, Karol; Weyrich, Tim; Krivánek, Jaroslav; Mitra, Niloy and Viola, Ivan
With the wider availability of full-color 3D printers, color-accurate 3D-print preparation has received increased attention. A key challenge lies in the inherent translucency of commonly used print materials that blurs out details of the color texture. Previous work tries to compensate for these scattering effects through strategic assignment of colored primary materials to printer voxels. To date, the highest-quality approach uses iterative optimization that relies on computationally expensive Monte Carlo light transport simulation to predict the surface appearance from subsurface scattering within a given print material distribution; that optimization, however, takes in the order of days on a single machine. In our work, we dramatically speed up the process by replacing the light transport simulation with a data-driven approach. Leveraging a deep neural network to predict the scattering within a highly heterogeneous medium, our method performs around two orders of magnitude faster than Monte Carlo rendering while yielding optimization results of similar quality level. The network is based on an established method from atmospheric cloud rendering, adapted to our domain and extended by a physically motivated weight sharing scheme that substantially reduces the network size. We analyze its performance in an end-to-end print preparation pipeline and compare quality and runtime to alternative approaches, and demonstrate its generalization to unseen geometry and material values. This for the first time enables full heterogenous material optimization for 3D-print preparation within time frames in the order of the actual printing time.
Orthogonalized Fourier Polynomials for Signal Approximation and Transfer
(The Eurographics Association and John Wiley & Sons Ltd., 2021) Maggioli, Filippo; Melzi, Simone; Ovsjanikov, Maks; Bronstein, Michael M.; Rodolà, Emanuele; Mitra, Niloy and Viola, Ivan
We propose a novel approach for the approximation and transfer of signals across 3D shapes. The proposed solution is based on taking pointwise polynomials of the Fourier-like Laplacian eigenbasis, which provides a compact and expressive representation for general signals defined on the surface. Key to our approach is the construction of a new orthonormal basis upon the set of these linearly dependent polynomials. We analyze the properties of this representation, and further provide a complete analysis of the involved parameters. Our technique results in accurate approximation and transfer of various families of signals between near-isometric and non-isometric shapes, even under poor initialization. Our experiments, showcased on a selection of downstream tasks such as filtering and detail transfer, show that our method is more robust to discretization artifacts, deformation and noise as compared to alternative approaches.

Browse

Browsing 40-Issue 2 by Subject "Computing methodologies"

Results Per Page

Sort Options