Home > Search Results: Honzátko, David
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Generative neural networks in image reconstruction
 Honzátko, David ; Šorel, Michal (advisor) ; Zvirinský, Peter (referee)
Recent research in generative models came up with a promising approach to modelling the prior proba- bility of natural images. The architecture of these prior models is based on deep neural networks. Although these priors were primarily designed for generating new natural-like images, its potential use is much broader. One of the possible applications is to use these models for solving the inverse problems in low-level vision (i.e., image reconstruction). This usage is mainly possible because the architecture of these models allows computing the derivative of the prior probability with respect to the input image. The main objective of this thesis is to evaluate the usage of these prior models in image reconstruction. This thesis proposes a novel model-based optimization method to two image reconstruction problems - image denoising and single-image super-resolution (SISR). The proposed method uses optimization algorithms for finding the maximum-a- posteriori probability, which is defined using the above mentioned prior models. The experimental results demonstrate that the proposed approach achieves reconstruction performance competitive with the current state-of-the-art methods, especially regarding SISR.
Detailed record
GPU Acceleration of Advanced Image Denoising
 Honzátko, David ; Kruliš, Martin (advisor) ; Elek, Oskár (referee)
BM3D (Block-Matching and 3D Filtering) is one of the state-of-art image denoising methods. Efficient implementations of this method exist for the CPU; however, these implementations are time demanding. On common desktop computers, denoising of high-resolution images can reach several minutes. The main objective of this thesis is to design an implementation of the BM3D method that utilize raw computational power of the GPU. GPU offers significantly more computational cores than the CPU; however, due to the specific execution and memory model, algorithms for the GPU are very different from algorithms for the CPU. Therefore, this thesis presents both: the basic aspects of the GPU computing and the BM3D method itself. Last but not least, the final implementation is empirically evaluated against the existing implementations by a set of performance tests. Powered by TCPDF (www.tcpdf.org)
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English