VMV19

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632811

Browse

Now showing 1 - 10 of 10

Consistent Filtering of Videos and Dense Light-Fields Without Optic-Flow
(The Eurographics Association, 2019) Shekhar, Sumit; Semmo, Amir; Trapp, Matthias; Tursun, Okan; Pasewaldt, Sebastian; Myszkowski, Karol; Döllner, Jürgen; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
A convenient post-production video processing approach is to apply image filters on a per-frame basis. This allows the flexibility of extending image filters-originally designed for still images-to videos. However, per-image filtering may lead to temporal inconsistencies perceived as unpleasant flickering artifacts, which is also the case for dense light-fields due to angular inconsistencies. In this work, we present a method for consistent filtering of videos and dense light-fields that addresses these problems. Our assumption is that inconsistencies-due to per-image filtering-are represented as noise across the image sequence. We thus perform denoising across the filtered image sequence and combine per-image filtered results with their denoised versions. At this, we use saliency based optimization weights to produce a consistent output while preserving the details simultaneously. To control the degree-of-consistency in the final output, we implemented our approach in an interactive real-time processing framework. Unlike state-of-the-art inconsistency removal techniques, our approach does not rely on optic-flow for enforcing coherence. Comparisons and a qualitative evaluation indicate that our method provides better results over state-of-the-art approaches for certain types of filters and applications.
Joint Schedule and Layout Autotuning for Sparse Matrices with Compound Entries on GPUs
(The Eurographics Association, 2019) Mueller-Roemer, Johannes Sebastian; Stork, André; Fellner, Dieter W.; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
Large sparse matrices with compound entries, i.e., complex and quaternionic matrices as well as matrices with dense blocks, are a core component of many algorithms in geometry processing, physically based animation, and other areas of computer graphics. We generalize several matrix layouts and apply joint schedule and layout autotuning to improve the performance of the sparse matrix-vector product on massively parallel graphics processing units. Compared to schedule tuning without layout tuning, we achieve speedups of up to 5.5x. In comparison to cuSPARSE, we achieve speedups of up to 4.7x
Learning a Perceptual Quality Metric for Correlation in Scatterplots
(The Eurographics Association, 2019) Wöhler, Leslie; Zou, Yuxin; Mühlhausen, Moritz; Albuquerque, Georgia; Magnor, Marcus; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
Visual quality metrics describe the quality and efficiency of multidimensional data visualizations in order to guide data analysts during exploration tasks. Current metrics are usually based on empirical algorithms which do not accurately represent human perception and therefore often differ from the analysts' expectations. We propose a new perception-based quality metric using deep learning that rates the correlation of data dimensions visualized by scatterplots. First, we created a data set containing over 15,000 pairs of scatterplots with human annotations on the perceived correlation between the data dimensions. Afterwards, we trained two different Convolutional Neural Networks (CNN), one extracts features from scatterplot images and the other directly from data vectors. We evaluated both CNNs on our test set and compared them to previous visual quality metrics. The experiments show that our new metric is able to represent human perception more accurately than previous methods.
Multi-Level-Memory Structures for Adaptive SPH Simulations
(The Eurographics Association, 2019) Winchenbach, Rene; Kolb, Andreas; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
In this paper we introduce a novel hash map-based sparse data structure for highly adaptive Smoothed Particle Hydrodynamics (SPH) simulations on GPUs. Our multi-level-memory structure is based on stacking multiple independent data structures, which can be created efficiently from the same particle data by utilizing self-similar particle orderings. Furthermore, we propose three neighbor list algorithms that improve performance, or significantly reduce memory requirements, when compared to Verlet-lists for the overall simulation. Overall, our proposed method significantly improves the performance of spatially adaptive methods, allows for the simulation of unbounded domains and reduces memory requirements without interfering with the simulation.
Normal Map Bias Reduction for Many-Lights Multi-View Photometric Stereo
(The Eurographics Association, 2019) Gan, Jiangbin; Bergen, Philipp; Thormählen, Thorsten; Drescher, Philip; Hagens, Ralf; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
In this paper, we improve upon an existing many-lights multi-view photometric stereo approach. Firstly, we show how to detect continuous regions for normal integration, which leads to a fully automatic reconstruction pipeline. Secondly, we compute perpixel light source visibilities using an initial biased reconstruction in order to update the estimated normal map to a solution with reduced bias. Thirdly, to further improve the normal accuracy, we compensate for interreflections of light between surface locations. Our approach is evaluated on both synthetic and real-world data and it is shown that the normal accuracy is improved by around 50 percent.
Polarization Demosaicking for Monochrome and Color Polarization Focal Plane Arrays
(The Eurographics Association, 2019) Qiu, Simeng; Fu, Qiang; Wang, Congli; Heidrich, Wolfgang ; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
Division-of-focal-plane (DoFP) polarization image sensors allow for snapshot imaging of linear polarization effects with inexpensive and straightforward setups. However, conventional interpolation based image reconstruction methods for such sensors produce unreliable and noisy estimates of quantities such as degree of linear polarization (DoLP) or angle of linear polarization (AoLP). In this paper, we propose a polarization demosaicking algorithm by inverting the polarization image formation model for both monochrome and color DoFP cameras. Compared to previous interpolation methods, our approach can significantly reduce noise induced artifacts and drastically increase the accuracy in estimating polarization states. We evaluate and demonstrate the performance of the methods on a new high-resolution color polarization dataset. Simulation and experimental results show that the proposed reconstruction and analysis tools offer an effective solution to polarization imaging.
Reconfigurable Snapshot HDR Imaging Using Coded Masks and Inception Network
(The Eurographics Association, 2019) Alghamdi, Masheal; Fu, Qiang; Thabet, Ali; Heidrich, Wolfgang ; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
High Dynamic Range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this paper we propose a joint design for snapshot HDR imaging by devising a spatially-varying modulation mask in the hardware as well as building an inception network to reconstruct the HDR image. We achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware-software solution offers a flexible yet robust way to modulating per-pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparison results show that our method outperforms state of the art in terms of visual perception quality.
RodMesh: Two-handed 3D Surface Modeling in Virtual Reality
(The Eurographics Association, 2019) Verhoeven, Floor; Sorkine-Hornung, Olga; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
User interfaces for 3D shape modeling in Virtual Reality (VR), unlike basic tasks such as text input and item selection, have been less explored in research so far. Shape modeling in 3D lends itself very well to VR, since the 3D immersion provides the user with richer spatial feedback and depth perception when compared to traditional 2D displays. That said, currently existing 3D modeling applications do not focus on optimizing the modeling interaction techniques for VR, but instead mostly merely port standard interaction paradigms. Our approach utilizes a popular sketch-based surface modeling algorithm in VR by rethinking the user interface in order to benefit from the 3D immersive environment and its inherent support of two-handed input. We propose a bimanual interaction technique that allows users to create 3D models via virtual deformable rods. These rods are bendable into outline shapes that are automatically inflated into manifold mesh surfaces, and can then be incrementally edited to further refine the shape.
Stochastic Convolutional Sparse Coding
(The Eurographics Association, 2019) Xiong, Jinhui; Richtarik, Peter; Heidrich, Wolfgang ; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. However, this approach is not without shortcomings. For example, Fourier-domain representations implicitly assume circular boundary conditions and make it hard to fully exploit the sparsity of the problem as well as the small spatial support of the filters. In this work, we propose a novel stochastic spatial-domain solver, in which a randomized subsampling strategy is introduced during the learning sparse codes. Afterwards, we extend the proposed strategy in conjunction with online learning, scaling the CSC model up to very large sample sizes. In both cases, we show experimentally that the proposed subsampling strategy, with a reasonable selection of the subsampling rate, outperforms the state-of-the-art frequency-domain solvers in terms of execution time without losing the learning quality. Finally, we evaluate the effectiveness of the over-complete dictionary learned from large-scale datasets, which demonstrates an improved sparse representation of the natural images on account of more abundant learned image features.
Trigonometric Moments for Editable Structured Light Range Finding
(The Eurographics Association, 2019) Werner, Sebastian; Iseringhausen, Julian; Callenberg, Clara; Hullin, Matthias; Schulz, Hans-Jörg and Teschner, Matthias and Wimmer, Michael
Structured-light methods remain one of the leading technologies in high quality 3D scanning, specifically for the acquisition of single objects and simple scenes. For more complex scene geometries, however, non-local light transport (e.g. interreflections, sub-surface scattering) comes into play, which leads to errors in the depth estimation. Probing the light transport tensor, which describes the global mapping between illumination and observed intensity under the influence of the scene can help to understand and correct these errors, but requires extensive scanning. We aim to recover a 3D subset of the full 4D light transport tensor, which represents the scene as illuminated by line patterns, rendering the approach especially useful for triangulation methods. To this end we propose a frequency-domain approach based on spectral estimation to reduce the number of required input images. Our method can be applied independently on each pixel of the observing camera, making it perfectly parallelizable with respect to the camera pixels. The result is a closed-form representation of the scene reflection recorded under line illumination, which, if necessary, masks pixels with complex global light transport contributions and, if possible, enables the correction of such measurements via data-driven semi-automatic editing.

Browse

Browsing VMV19 by Subject "Computing methodologies"

Results Per Page

Sort Options