Professor Eisemann is to be awarded the 2019 Dutch prize for ICT research (Nederlandse Prijs voor ICT-onderzoek). The well-deserved award is a recognition for Prof. Eisemann’s research into the accurate, detailed depiction of visualizations using modern graphics hardware. The prize will be officially awarded to Prof. Eisemann during the ICT Open 2019 in Hilversum. Congratulations to Prof. Eisemann!
Computer Graphics and Visualization Seminar on Thursday, March 7, 2019, 15:45-17:45h, at EWI-Lecture hall Chip.
The program features the following two speakers:
Remi van der Laan
Title: Exploiting Coherence in Time-Varying Voxel Data
Abstract: We encode time-varying voxel data for efficient storage and streaming. We store the equivalent of a separate sparse voxel octree for each frame, but utilize both spatial and temporal coherence to reduce the amount of memory needed. We represent the time-varying voxel data in a single directed acyclic graph with one root per time step. In this graph, we avoid storing identical regions by keeping one unique instance and pointing to that from several parents. We further reduce the memory consumption of the graph by minimizing the number of bits per pointer and encoding the result into a dense bitstream.
Michiel van Spaendonck
Title: Spatiotemporal Variance-Guided Filtering: Real-Time Reconstruction for Path-Traced Global Illumination
Abstract: We introduce a reconstruction algorithm that generates a temporally stable sequence of images from one path-per-pixel global illumination. To handle such noisy input, we use temporal accumulation to increase the effective sample count and spatiotemporal luminance variance estimates to drive a hierarchical, image-space wavelet filter. This hierarchy allows us to distinguish between noise and detail at multiple scales using local luminance variance.
Physically based light transport is a long-standing goal for real-time computer graphics. While modern games use limited forms of ray tracing, physically based Monte Carlo global illumination does not meet their 30Hz minimal performance requirement. Looking ahead to fully dynamic real-time path tracing, we expect this to only be feasible using a small number of paths per pixel. As such, image reconstruction using low sample counts is key to bringing path tracing to real-time. When compared to prior interactive reconstruction filters, our work gives approximately 10x more temporally stable results, matches reference images 5-47% better (according to SSIM), and runs in just 10ms (+- 15%) on modern graphics hardware at 1920×1080 resolution.
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, February 21, 2019, 15:45-17:45h, at EWI-Lecture hall Chip.
The program features the following two speakers:
Nouri Khalass
Title: Visualizing Stars and Emission Nebulae
Abstract: We describe the star and nebula visualization techniques used to create a 3D volumetric visualization of the Orion Nebula. The nebula’s ionization layer is modeled first as a surface model, derived from infrared and visible light observations. The model is imported into a volume scene graph-based volume visualization system to simulate the nebula’s emissive gases. Stars are rendered using Gaussian spots that are attenuated with distance.
Mark van de Ruit
Title: Real-Time Polygonal-Light Shading with Linearly Transformed Cosines
Abstract: In this paper, we show that applying a linear transformation—represented by a 3 x 3 matrix—to the direction vectors of a spherical distribution yields another spherical distribution, for which we derive a closed-form expression. With this idea, we can use any spherical distribution as a base shape to create a new family of spherical distributions with parametric roughness, elliptic anisotropy and skewness. If the original distribution has an analytic expression, normalization, integration over spherical polygons, and importance sampling, then these properties are inherited by the linearly transformed distributions.
By choosing a clamped cosine for the original distribution we obtain a family of distributions, which we call Linearly Transformed Cosines (LTCs), that provide a good approximation to physically based BRDFs and that can be analytically integrated over arbitrary spherical polygons. We show how to use these properties in a realtime polygonal-light shading application. Our technique is robust, fast, accurate and simple to implement.
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, February 7, 2019, 15:45-17:45h, at EWI-Lecture hall Chip.
The program features the following two speakers:
Haoming Yeh
Title: Projective Dynamics: Fusing Constraint Projections for Fast Simulation
Abstract: We present a new method for implicit time integration of physical systems. Our approach builds a bridge between nodal Finite Element methods and Position Based Dynamics, leading to a simple, efficient, robust, yet accurate solver that supports many different types of constraints. We propose specially designed energy potentials that can be solved efficiently using an alternating optimization approach. Inspired by continuum mechanics, we derive a set of continuum based potentials that can be efficiently incorporated within our solver. We demonstrate the generality and robustness of our approach in many different applications ranging from the simulation of solids,
cloths, and shells, to example-based simulation. Comparisons to Newton-based and Position Based Dynamics solvers highlight the benefits of our formulation.
Matthijs Amesz
Title: Inverse Diffusion Curves using Shape Optimization
Abstract: The inverse diffusion curve problem focuses on automatic creation of diffusion curve images that resemble user provided color fields. This problem is challenging since the 1D curves have a
nonlinear and global impact on resulting color fields via a partial differential equation (PDE). We introduce a new approach complementary to previous methods by optimizing curve geometry.
In particular, we propose a novel iterative algorithm based on the theory of shape derivatives. The resulting diffusion curves are clean and well-shaped, and the final image closely approximates
the input. Our method provides a user-controlled parameter to regularize curve complexity, and generalizes to handle input color fields represented in
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, January 10, 2019, 15:45-17:45h, at Pulse-Hall 4.
The program features the following two speakers:
Anmol Hanagodimath
Title:
Optimizing BRDF Orientations for the Manipulation of Anisotropic Highlights
Abstract:
This paper introduces a system for the direct editing of highlights produced by anisotropic BRDFs, which we call anisotropic highlights. We first provide a comprehensive analysis of the link between the direction of anisotropy and the shape of highlight curves for arbitrary object surfaces. The gained insights provide the required ingredients to infer BRDF orientations from a prescribed highlight tangent field. This amounts to a non-linear optimization problem, which is solved at interactive framerates during manipulation. Taking inspiration from sculpting software, we provide tools that give the impression of manipulating highlight curves while actually modifying their tangents. Our solver produces desired highlight shapes for a host of lighting environments and anisotropic BRDFs
Shang Xiang
Title:
The Heat Method for Distance Computation
Abstract:
We introduce the heat method for solving the single- or multiple-source shortest path problem on both flat and curved domains. A key insight is that distance computation can be split into two stages: first find the direction along which distance is increasing, then compute the distance itself. The heat method is robust, efficient, and simple to implement since it is based on solving a pair of standard sparse linear systems. These systems can be factored once and subsequently solved in near-linear time, substantially reducing amortized cost. Real-world performance is an order of magnitude faster than state-of-the-art methods, while maintaining a comparable level of accuracy. The method can be applied in any dimension, and on any domain that admits a gradient and inner product—including regular grids, triangle meshes, and point clouds. Numerical evidence indicates that the method converges to the exact distance in the limit of refinement; we also explore smoothed approximations of distance suitable for applications where greater regularity is desired.
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, December 13th, 2018, 15:45-17:45h, at Pulse-Hall 2.
The program features the following two speakers:
Marie Kegeleers
Title: Soccer on Your Tabletop
Abstract: We present a system that transforms a monocular video of a soccer game into a moving 3D reconstruction, in which the players and field can be rendered interactively with a 3D viewer or through an Augmented Reality device. At the heart of our paper is an approach to estimate the depth map of each player, using a CNN that is trained on 3D player data extracted from soccer video games. We compare with state of the art body pose and depth estimation techniques, and show results on both synthetic ground truth benchmarks, and real YouTube soccer footage.
Levi van Aanholt
Title: Interactive Sketching of Urban Procedural Models
Abstract: 3D modeling remains a notoriously difficult task for novices de- spite significant research effort to provide intuitive and automated systems. We tackle this problem by combining the strengths of two popular domains: sketch-based modeling and procedural modeling. On the one hand, sketch-based modeling exploits our ability to draw but requires detailed, unambiguous drawings to achieve complex models. On the other hand, procedural modeling automates the creation of precise and detailed geometry but requires the tedious definition and parameterization of procedural models. Our system uses a collection of simple procedural grammars, called snippets, as building blocks to turn sketches into realistic 3D models. We use a machine learning approach to solve the inverse problem of finding the procedural model that best explains a user sketch. We use non-photorealistic rendering to generate artificial data for training convolutional neural networks capable of quickly recognizing the procedural rule intended by a sketch and estimating its parameters. We integrate our algorithm in a coarse-to-fine urban modeling system that allows users to create rich buildings by successively sketching the building mass, roof, facades, windows, and ornaments. A user study shows that by using our approach non-expert users can generate complex buildings in just a few minutes.
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, November 29th, 2018, 15:45-17:45h, at Pulse-Hall 2.
The program features the following two speakers:
Jasper van Esveld
Title
CoreCavity: Interactive Shell Decomposition for Fabrication with
Abstract
Molding is a popular mass production method, in which the initial expenses for the mold are offset by the low per-unit production cost. However, the physical fabrication constraints of the molding technique commonly restrict the shape of moldable objects. For a complex shape, a decomposition of the object into moldable parts is a common strategy to address these constraints, with plastic model kits being a popular and illustrative example. However, conducting such a decomposition requires considerable expertise, and it depends on the technical aspects of the fabrication technique, as well as aesthetic considerations. We present an interactive technique to create such decompositions for two-piece molding, in which each part of the object is cast between two rigid mold pieces. Given the surface description of an object, we decompose its thin-shell equivalent into moldable parts by first performing a coarse decomposition and then utilizing an active contour model for the boundaries between individual parts. Formulated as an optimization problem, the movement of the contours is guided by an energy reflecting fabrication constraints to ensure the moldability of each part. Simultaneously the user is provided with editing capabilities to enforce aesthetic guidelines. Our interactive interface provides control of the contour positions by allowing, for example, the alignment of part boundaries with object features. Our technique enables a novel workflow, as it empowers novice users to explore the design space, and it generates fabrication-ready two-piece molds that can be used either for casting or industrial injection molding of free-form objects.
Bartosz Zablocki
Title
High-quality streamable free-viewpoint video
Abstract
We present the first end-to-end solution to create high-quality free-viewpoint video encoded as a compact data stream. Our system records performances using a dense set of RGB and IR video cameras, generates dynamic textured surfaces, and compresses these to a streamable 3D video format. Four technical advances contribute to high fidelity and robustness: multimodal multi-view stereo fusing RGB, IR, and silhouette information; adaptive meshing guided by automatic detection of perceptually salient areas; mesh tracking to create temporally coherent subsequences; and encoding of tracked textured meshes as an MPEG video stream. Quantitative experiments demonstrate geometric accuracy, texture fidelity, and encoding efficiency. We release several datasets with calibrated inputs and processed results to foster future research.
You are cordially invited to attend the MSc thesis defence of Niels van der Veen. This defense will take place on Friday the 23rd of November, at 12:00h in room LB01.010, building 36.
The presentation is open to the public and will last around 45 minutes including questions from the audience. You are hereby cordially invited to join!
Title
A paint-based approach for optimal lighting design in real scenes
Abstract
Lighting design is a computational expensive task, commonly done using Computer-aided design (CAD) software in a virtual scene. The designer places and tunes the virtual light sources and, yet the virtual environment is ideal for physically correct light tracing, the costly simulation might not provide the desired impression in the real scene. Moreover, the chosen light placement is not necessarily optimized. In this work we capture light behavior from real scenes as well as 3D scene properties and use this information to recreate different lighting designs. The results approximates physical correctness while visualizing the illumination on the real scene in a more time-efficient way. To make the design process more intuitive, the user paints the desired light properties instead of placing the light sources. The system attempts to find valid positions and parameters of the light sources in the scene to reflect the current design. Constraints such as number of light sources and emission profiles as well as spatial constraints can also be specified.
Committee
Prof. Dr. Elmar Eisemann
Dr. Klaus Hildebrandt
Dr. R. Venkatesha Prasad
You are cordially invited to attend our Computer Graphics and Visualization Research Seminar on Thursday, November 22nd, 2018, 13:00-14:00, at VMB COLLOQUIUMZAAL.
The program features an invited talk:
Speaker: Dr. Jun Wu
Assistant Professor, Department of Design Engineering, Delft University of Technology
Title: Topology Optimization of Multiscale Structures for 3D Printing
Abstract: 3D printing enables the fabrication of complex structures. In engineering the benefits of this manufacturing flexibility are probably best demonstrated in combination with the design of structures by topology optimization. In this talk I will present our research on topology optimization of multiscale structures. The first approach, inspired by trabecular bone, generates porous bone-like infill structures for 3D printing. This approach is extended to allow simultaneous optimization of shape boundaries and the interior lattice. To reduce its computational complexity, a homogenization-based approach is developed to project orthotropic lattice structures. In the second approach, we develop a continuous formulation to the discrete problem of quadtree subdivision. By restricting the subdivision level, geometric features such as maximum and minimum structure sizes can be controlled, for manufacturing benefits.
Images of optimized structures and fabrication results can be found on this page.
You are cordially invited to attend our Computer Graphics and Visualization Seminar on Thursday, November 15th, 2018, 15:45-17:45h, at Pulse-Hall 2.
The program features the following two speakers:
Huinan Jiang
Title
A Chebyshev Semi-Iterative Approach for Accelerating Projective and Position-based Dynamics
Abstract
In this paper, we study the use of the Chebyshev semi-iterative approach in projective and position-based dynamics. Although projective dynamics is fundamentally nonlinear, its convergence behavior is similar to that of an iterative method solving a linear system. Because of that, we can estimate the “spectral radius” and use it in the Chebyshev approach to accelerate the convergence by at least one order of magnitude, when the global step is handled by the direct solver, the Jacobi solver, or even the Gauss-Seidel solver. Our experiment shows that the combination of the Chebyshev approach and the direct solver runs fastest on CPU, while the combination of the Chebyshev approach and the Jacobi solver outperforms any other combination on GPU, as it is highly compatible with parallel computing. Our experiment further shows position-based dynamics can be accelerated by the Chebyshev approach as well, although the effect is less obvious for tetrahedral meshes. The whole approach is simple, fast, effective, GPU-friendly, and has a small memory cost.
Jesse Tilro
Title
Phase-Functioned Neural Networks for Character Control
Abstract
We present a real-time character control mechanism using a novel neural network architecture called a Phase-Functioned Neural Network. In this network structure, the weights are computed via a cyclic function which uses the phase as an input. Along with the phase, our system takes as input user controls, the previous state of the character, the geometry of the scene, and automatically produces high quality motions that achieve the desired user control. The entire network is trained in an end-to-end fashion on a large dataset composed of locomotion such as walking, running, jumping, and climbing movements fitted into virtual environments. Our system can therefore automatically produce motions where the character adapts to different geometric environments such as walking and running over rough terrain, climbing over large rocks, jumping over obstacles, and crouching under low ceilings. Our network architecture produces higher quality results than time-series autoregressive models such as LSTMs as it deals explicitly with the latent variable of motion relating to the phase. Once trained, our system is also extremely fast and compact, requiring only milliseconds of execution time and a few megabytes of memory, even when trained on gigabytes of motion data. Our work is most appropriate for controlling characters in interactive scenes such as computer games and virtual reality systems.
