EG 2021 - Posters
Permanent URI for this collection
Posters
Rendering 2D Vector Graphics on Mobile GPU Devices
] [
]
Harish Kumar and Anmol Sud
Illumination-driven Light Probe Placement
Konstantinos Vardis, Andreas Alexandros Vasilakis, and Georgios Papaioannou
Color Reproduction Framework for Inkjet FDM 3D Printers
Piyarat Silapasuphakornwong, Parinya Punpongsanon, Chulapong Panichkriangkrai, Suchitra
Sueeprasan, and Kazutake Uehira
To Splat Straight with Crooked Points: Rendering Noisy Meshes and Point Clouds using
Coherent Tangent Vector Fields
Rafael Kuffner dos Anjos and Daniel S. Lopes
Generative Landmarks
David Ferman and Gaurav Bharaj
Unsupervised Learning of Disentangled 3D Representation from a Single Image
Junliang Lv, Haiyong Jiang, and Jun Xiao
Tetrahedral Interpolation on Regular Grids
Róbert Bán and Gábor Valasek
An Unbiased Hybrid Rendering Approach to Path Guiding
Jia-Wun Jhang and Chun-Fa Chang
Fast and Robust Registration and Calibration of Depth-Only Sensors
Andre Mühlenbrock, Roland Fischer, René Weller, and Gabriel Zachmann
Browse
Recent Submissions
Item Rendering 2D Vector Graphics on Mobile GPU Devices(The Eurographics Association, 2021) Kumar, Harish; Sud, Anmol; Bittner, Jirí and Waldner, ManuelaDesigners and artists world-wide rely on vector graphics to design and edit 2D artwork, illustrations and typographic content. There is a recent trend of vector graphic applications moving to mobile platforms such as iPads, iPhone and mobile phones and with that there is new interest in optimised techniques of rendering vector graphics on these devices. These vector applications are not read only but also requires real time vector editing experience. Our solution builds upon standard 'stencil then cover' paradigm and develops an algorithm targeted for GPUs based on tile based deferred rendering architecture. Our technique provides an efficient way to use signed distance based anti-aliasing techniques with 'stencil then cover' paradigm by employing a state machine during the fragment shader stage of graphics pipeline.Item Illumination-driven Light Probe Placement(The Eurographics Association, 2021) Vardis, Konstantinos; Vasilakis, Andreas Alexandros; Papaioannou, Georgios; Bittner, Jirí and Waldner, ManuelaWe introduce a simplification method for light probe configurations that preserves the indirect illumination distribution in scenes with diverse lighting conditions. An iterative graph simplification algorithm discards the probes that, according to a set of evaluation points, have the least impact on the global light field. Our approach is simple, generic and aims at improving the repetitive and often non-intuitive and tedious task of placing light probes on complex virtual environments.Item Color Reproduction Framework for Inkjet FDM 3D Printers(The Eurographics Association, 2021) Silapasuphakornwong, Piyarat; Punpongsanon, Parinya; Panichkriangkrai, Chulapong; Sueeprasan, Suchitra; Uehira, Kazutake; Bittner, Jirí and Waldner, ManuelaRecent advances in consumer-grade 3D printers have enabled the fabrication of personal artifacts in aesthetically pleasing full color. However, the printed colors are usually different from the actual user desired colors due to the mismatching of droplets when the color reproduction workflow has been changed or the color profile setup is missing. In this paper, we present a preliminary experiment to investigate color reproduction errors in consumer-grade inkjet FDM 3D printers. Our results suggest that solving the problem requires initiating the workflow to minimize color reproduction errors such as using CMYK or sRGB color profiles. We also found that the mismatched color gamut between the input's desired texture and the 3D printed output depends on different file formats, and this finding requires future investigation.Item Generative Landmarks(The Eurographics Association, 2021) Ferman, David; Bharaj, Gaurav; Bittner, Jirí and Waldner, ManuelaWe propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistency in annotations over a temporal volume leads to sub-optimal landmark learning. Further, high-quality landmarks with personalization is often hard to achieve. We pose landmark detection as an image translation problem. We capture two sets of unpaired marked (with paint) and unmarked videos. We then use a generative adversarial network and cyclic consistency to predict deformations of landmark templates that simulate markers on unmarked images until these images are indistinguishable from ground-truth marked images. Our novel method does not rely on manually labelled priors, is temporally consistent, and image class agnostic - face, and hand landmarks detection examples are shown.Item To Splat Straight with Crooked Points: Rendering Noisy Meshes and Point Clouds using Coherent Tangent Vector Fields(The Eurographics Association, 2021) Anjos, Rafael Kuffner dos; Lopes, Daniel S.; Bittner, Jirí and Waldner, ManuelaSurface aligned splatting is a popular rendering technique to visualize reconstructed meshes and point clouds scanned from the real world. Such data typically presents some degree of noise that jeopardizes any attempt to render a perfectly smooth normal field and, more importantly, the estimated tangent vector fields are not locally continuous, thus affecting the overall visual quality. In this work, we compare two splat orientation techniques for rendering 3D noisy data, namely, the Covariance Matrix and the Householder formula. We evaluate both techniques using four publicly available meshes with synthetic noise, and four scanned point clouds with natural noise. Results indicate that the Householder technique is better suited for surface aligned splatting as it generates more coherent tangent vector fields, while Covariance Matrix reacts poorly to noise.Item Tetrahedral Interpolation on Regular Grids(The Eurographics Association, 2021) Bán, Róbert; Valasek, Gábor; Bittner, Jirí and Waldner, ManuelaThis work proposes the use of barycentric interpolation on enclosing simplices of sample points to infer a reconstructed function from discrete data. In particular, we compare the results of trilinear and tetrahedral interpolation over regular 3D grids of second order spherical harmonics (SH) light probes. In general, tetrahedral interpolation only requires four data samples per query in contrast to the 8 samples necessary for trilinear interpolation, at the expense of a more expensive weight computation. Our tetrahedral implementation subdivides the cubical cells into six tetrahedra and uses the barycentric coordinates of the query position as weights to blend the probe data. We show that barycentric coordinates can be calculated efficiently in shaders for our particular tetrahedral decomposition of the cube, resulting only in simple arithmetic and conditional move operations.Item Unsupervised Learning of Disentangled 3D Representation from a Single Image(The Eurographics Association, 2021) Lv, Junliang; Jiang, Haiyong; Xiao, Jun; Bittner, Jirí and Waldner, ManuelaLearning 3D representation of a single image is challenging considering the ambiguity, occlusion, and perspective project of an object in an image. Previous works either seek image annotation or 3D supervision to learn meaningful factors of an object or employ a StyleGAN-like framework for image synthesis. While the first ones rely on tedious annotation and even dense geometry ground truth, the second solutions usually cannot guarantee consistency of shapes between different view images. In this paper, we combine the advantages of both frameworks and propose an image disentanglement method based on 3D representation. Results show our method facilitates unsupervised 3D representation learning while preserving consistency between images.Item An Unbiased Hybrid Rendering Approach to Path Guiding(The Eurographics Association, 2021) Jhang, Jia-Wun; Chang, Chun-Fa; Bittner, Jirí and Waldner, ManuelaWhen we think of hybrid rendering of rasterization and ray tracing, we often consider rasterization as a mean to solve the primary rays and then consider ray tracing as a mean to add secondary effects. We take a different approach to combine ray tracing and rasterization, in which our final output images are still produced with a path tracer. We leverage the GPU rasterization to build the necessary data that are required for path guidng, thus improves the convergence of our path tracer. We borrow the ideas of Voxel Cone Tracing and implement it in GPU shaders to build the path guiding data. The advantage of our proposed hybrid approach is that it maintains the unbiased results of a Monte Carlo path tracer while incurring relatively small performance hit in path guiding, as shown in our preliminary results.Item Fast and Robust Registration and Calibration of Depth-Only Sensors(The Eurographics Association, 2021) Mühlenbrock, Andre; Fischer, Roland; Weller, René; Zachmann, Gabriel; Bittner, Jirí and Waldner, ManuelaThe precise registration between multiple depth cameras is a crucial prerequisite for many applications. Previous techniques frequently rely on RGB or IR images and checkerboard targets for feature detection, partly due to the depth data being inherently noisy. This limitation prohibits the usage for use-cases where neither is available. We present a novel registration approach that solely uses depth data for feature detection, making it more universally applicable while still achieving robust and precise results. We propose a combination of a custom 3D registration target - a lattice with regularly-spaced holes - and a feature detection algorithm that is able to reliably extract the lattice and its features from noisy depth images.Item EUROGRAPHICS 2021: Posters Frontmatter(Eurographics Association, 2021) Bittner, Jirí; Waldner, Manuela; Bittner, Jirí and Waldner, Manuela