| 1. |
- Baravdish, Gabriel, et al.
(författare)
-
GPU Accelerated SL0 for Multidimensional Signals
- 2021
-
Ingår i: 50TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOP PROCEEDINGS - ICPP WORKSHOPS 21. - New York, NY, USA : ASSOC COMPUTING MACHINERY. - 9781450384414
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a novel GPU-based method for highly parallel compressed sensing of n-dimensional (nD) signals based on the smoothed l(0) (SL0) algorithm. We demonstrate the efficiency of our approach by showing several examples of nD tensor reconstructions. Moreover, we also consider the traditional 1D compressed sensing, and compare the results. We show that the multidimensional SL0 algorithm is computationally superior compared to the 1D variant due to the small dictionary sizes per dimension. This allows us to fully utilize the GPU and perform massive batch-wise computations, which is not possible for the 1D compressed sensing using SL0. For our evaluations, we use light field and light field video data sets. We show that we gain more than an order of magnitude speedup for both one-dimensional as well as multidimensional data points compared to a parallel CPU implementation. Finally, we present a theoretical analysis of the SL0 algorithm for nD signals, which generalizes previous work for 1D signals.
|
|
| 2. |
- Baravdish, Gabriel, 1992-, et al.
(författare)
-
GPU Accelerated Sparse Representation of Light Fields
- 2019
-
Ingår i: VISIGRAPP - 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Prague, Czech Republic, February 25-27, 2019.. - : SCITEPRESS. - 9789897583544 ; , s. 177-182
-
Konferensbidrag (refereegranskat)abstract
- We present a method for GPU accelerated compression of light fields. The approach is by using a dictionary learning framework for compression of light field images. The large amount of data storage by capturing light fields is a challenge to compress and we seek to accelerate the encoding routine by GPGPU computations. We compress the data by projecting each data point onto a set of trained multi-dimensional dictionaries and seek the most sparse representation with the least error. This is done by a parallelization of the tensor-matrix product computed on the GPU. An optimized greedy algorithm to suit computations on the GPU is also presented. The encoding of the data is done segmentally in parallel for a faster computation speed while maintaining the quality. The results shows an order of magnitude faster encoding time compared to the results in the same research field. We conclude that there are further improvements to increase the speed, and thus it is not too far from an interacti ve compression speed.
|
|
| 3. |
- Baravdish, George, 1964-, et al.
(författare)
-
Learning via nonlinear conjugate gradients and depth-varying neural ODEs
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- The inverse problem of supervised reconstruction of depth-variable (time-dependent) parameters in a neural ordinary differential equation (NODE) is considered, that means finding the weights of a residual network with time continuous layers. The NODE is treated as an isolated entity describing the full network as opposed to earlier research, which embedded it between pre- and post-appended layers trained by conventional methods. The proposed parameter reconstruction is done for a general first order differential equation by minimizing a cost functional covering a variety of loss functions and penalty terms. A nonlinear conjugate gradient method (NCG) is derived for the minimization. Mathematical properties are stated for the differential equation and the cost functional. The adjoint problem needed is derived together with a sensitivity problem. The sensitivity problem can estimate changes in the network output under perturbation of the trained parameters. To preserve smoothness during the iterations the Sobolev gradient is calculated and incorporated. As a proof-of-concept, numerical results are included for a NODE and two synthetic datasets, and compared with standard gradient approaches (not based on NODEs). The results show that the proposed method works well for deep learning with infinite numbers of layers, and has built-in stability and smoothness.
|
|
| 4. |
- Bylow, Erik, et al.
(författare)
-
Combining Depth Fusion and Photometric Stereo for Fine-Detailed 3D Models
- 2019
-
Ingår i: Image Analysis - 21st Scandinavian Conference, SCIA 2019, Proceedings. - Cham : Springer International Publishing. - 0302-9743 .- 1611-3349. - 9783030202040 ; 11482 LNCS, s. 261-274
-
Konferensbidrag (refereegranskat)abstract
- In recent years, great progress has been made on the problem of 3D scene reconstruction using depth sensors. On a large scale, these reconstructions look impressive, but often many fine details are lacking due to limitations in the sensor resolution. In this paper we combine two well-known principles for recovery of 3D models, namely fusion of depth images with photometric stereo to enhance the details of the reconstructions. We derive a simple and transparent objective functional that takes both the observed intensity images and depth information into account. The experimental results show that many details are captured that are not present in the input depth images. Moreover, we provide a quantitative evaluation that confirms the improvement of the resulting 3D reconstruction using a 3D printed model.
|
|
| 5. |
- Dumke, Roger, et al.
(författare)
-
Multi-center evaluation of one commercial and 12 in-house real-time PCR assays for detection of Mycoplasma pneumoniae
- 2017
-
Ingår i: Diagnostic microbiology and infectious disease. - : ELSEVIER SCIENCE INC. - 0732-8893 .- 1879-0070. ; 88:2, s. 111-114
-
Tidskriftsartikel (refereegranskat)abstract
- Detection of Mycoplasma pneumoniae by real-time PCR is not yet standardized across laboratories. We have implemented a standardization protocol to compare the performance of thirteen commercial and in-house approaches. Despite differences on threshold values of samples, all assays were able to detect at least 20 M. pneumoniae genomes per reaction.
|
|
| 6. |
- Eilertsen, Gabriel, et al.
(författare)
-
A comparative review of tone-mapping algorithms for high dynamic range video
- 2017
-
Ingår i: Computer graphics forum (Print). - : WILEY. - 0167-7055 .- 1467-8659. ; 36:2, s. 565-592
-
Tidskriftsartikel (refereegranskat)abstract
- Tone-mapping constitutes a key component within the field of high dynamic range (HDR) imaging. Its importance is manifested in the vast amount of tone-mapping methods that can be found in the literature, which are the result of an active development in the area for more than two decades. Although these can accommodate most requirements for display of HDR images, new challenges arose with the advent of HDR video, calling for additional considerations in the design of tone-mapping operators (TMOs). Today, a range of TMOs exist that do support video material. We are now reaching a point where most camera captured HDR videos can be prepared in high quality without visible artifacts, for the constraints of a standard display device. In this report, we set out to summarize and categorize the research in tone-mapping as of today, distilling the most important trends and characteristics of the tone reproduction pipeline. While this gives a wide overview over the area, we then specifically focus on tone-mapping of HDR video and the problems this medium entails. First, we formulate the major challenges a video TMO needs to address. Then, we provide a description and categorization of each of the existing video TMOs. Finally, by constructing a set of quantitative measures, we evaluate the performance of a number of the operators, in order to give a hint on which can be expected to render the least amount of artifacts. This serves as a comprehensive reference, categorization and comparative assessment of the state-of-the-art in tone-mapping for HDR video.
|
|
| 7. |
- Eilertsen, Gabriel, et al.
(författare)
-
A HIGH DYNAMIC RANGE VIDEO CODEC OPTIMIZED BY LARGE-SCALE TESTING
- 2016
-
Ingår i: 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP). - : IEEE. - 9781467399616 ; , s. 1379-1383
-
Konferensbidrag (refereegranskat)abstract
- While a number of existing high-bit depth video compression methods can potentially encode high dynamic range (HDR) video, few of them provide this capability. In this paper, we investigate techniques for adapting HDR video for this purpose. In a large-scale test on 33 HDR video sequences, we compare 2 video codecs, 4 luminance encoding techniques (transfer functions) and 3 color encoding methods, measuring quality in terms of two objective metrics, PU-MSSIM and HDR-VDP-2. From the results we design an open source HDR video encoder, optimized for the best compression performance given the techniques examined.
|
|
| 8. |
- Eilertsen, Gabriel, et al.
(författare)
-
A versatile material reflectance measurement system for use in production
- 2011
-
Ingår i: Proceedings of SIGRAD 2011. Evaluations of Graphics and Visualization — Efficiency, Usefulness, Accessibility, Usability, November 17–18, 2011, KTH, Stockholm, Sweden. - : Linköping University Electronic Press. - 9789173930086 ; , s. 69-76
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present our developed bidirectional reflectance distribution capturing pipeline. It includes a constructed gonioreflectometer for reflectance measurements, as well as extensive software for operation, data visualization and parameter fitting of analytic models. Our focus is on the flexible user interface, aimed at material appearance creation for computer graphics, and targeted both for production and research employment.Key challenges have been in providing a user friendly and effective software for functioning in a production environment, abstracting the details of the calculations involved in the reflectance capturing and fitting. We show how a combination of well-tuned tools can make complex processes such as reflectance calibration, measurement and fitting highly automated in a fast and easy work-flow, from material scanning to model parameters optimized for use in rendering. At the same time, the developed software provides a modifiable interface for detailed control. The importance of having good reflectance visualizations is also demonstrated, where the software plotting tools are able to show vital details of a reflectance distribution, giving valuable insight in to a materials properties and a models accuracy of fit to measured data, on both a local and global level.
|
|
| 9. |
- Eilertsen, Gabriel, 1984-, et al.
(författare)
-
BriefMatch: Dense binary feature matching for real-time optical flow estimation
- 2017
-
Ingår i: Proceedings of the Scandinavian Conference on Image Analysis (SCIA17). - Cham : Springer. - 9783319591254 ; , s. 221-233
-
Konferensbidrag (refereegranskat)abstract
- Research in optical flow estimation has to a large extent focused on achieving the best possible quality with no regards to running time. Nevertheless, in a number of important applications the speed is crucial. To address this problem we present BriefMatch, a real-time optical flow method that is suitable for live applications. The method combines binary features with the search strategy from PatchMatch in order to efficiently find a dense correspondence field between images. We show that the BRIEF descriptor provides better candidates (less outlier-prone) in shorter time, when compared to direct pixel comparisons and the Census transform. This allows us to achieve high quality results from a simple filtering of the initially matched candidates. Currently, BriefMatch has the fastest running time on the Middlebury benchmark, while placing highest of all the methods that run in shorter than 0.5 seconds.
|
|
| 10. |
- Eilertsen, Gabriel, 1984-, et al.
(författare)
-
Classifying the classifier : dissecting the weight space of neural networks
- 2020
-
Ingår i: Proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020). - : IOS PRESS. - 9781643681016 ; , s. 1119-1126
-
Konferensbidrag (refereegranskat)abstract
- This paper presents an empirical study on the weights of neural networks, where we interpret each model as a point in a high-dimensional space – the neural weight space. To explore the complex structure of this space, we sample from a diverse selection of training variations (dataset, optimization procedure, architecture,etc.) of neural network classifiers, and train a large number of models to represent the weight space. Then, we use a machine learning approach for analyzing and extracting information from this space. Most centrally, we train a number of novel deep meta-classifiers withthe objective of classifying different properties of the training setup by identifying their footprints in the weight space. Thus, the meta-classifiers probe for patterns induced by hyper-parameters, so that we can quantify how much, where, and when these are encoded through the optimization process. This provides a novel and complementary view for explainable AI, and we show how meta-classifiers can reveal a great deal of information about the training setup and optimization, by only considering a small subset of randomly selected consecutive weights. To promote further research on the weight space, we release the neural weight space (NWS) dataset – a collection of 320K weightsnapshots from 16K individually trained deep neural networks.
|
|
