National Repository of Grey Literature 4 records found  Search took 0.00 seconds. 
Texture Synthesis
Havelka, Robert ; Štancl, Vít (referee) ; Švub, Miroslav (advisor)
This thesis deals with texturing, its importance and basic list of the processes during texture synthetising is included. Texture generating is mainly described from the procedural generator point of view. There is also explained the sense of using Fourier's transformation and its simplified version, the discreet cosine transformation. For texture modiffication, Gaussian noise and gaussian filter is used. The convolution theorem is applied for the texture mixing. Within the scope of this thesis, there is also described the application implementation, which enables experimenting with texture creating.
Removing noise in images using deep learning methods
Strejček, Jakub ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
This thesis focuses on comparing methods of denoising by deep learning and their implementation. In the last few years, it has become clear that it is not necessary to have paired data, as for noisy and clean pictures, to train convolution neural networks but it is sufficient to have only noisy pictures for denoising in particular cases. By using methods described in this thesis it is possible to effectively remove i.e. additive Gaussian noise and what more, it is possible to achieve better results than by using statistic methods, which are being used for denoising these days.
Removing noise in images using deep learning methods
Strejček, Jakub ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
This thesis focuses on comparing methods of denoising by deep learning and their implementation. In the last few years, it has become clear that it is not necessary to have paired data, as for noisy and clean pictures, to train convolution neural networks but it is sufficient to have only noisy pictures for denoising in particular cases. By using methods described in this thesis it is possible to effectively remove i.e. additive Gaussian noise and what more, it is possible to achieve better results than by using statistic methods, which are being used for denoising these days.
Texture Synthesis
Havelka, Robert ; Štancl, Vít (referee) ; Švub, Miroslav (advisor)
This thesis deals with texturing, its importance and basic list of the processes during texture synthetising is included. Texture generating is mainly described from the procedural generator point of view. There is also explained the sense of using Fourier's transformation and its simplified version, the discreet cosine transformation. For texture modiffication, Gaussian noise and gaussian filter is used. The convolution theorem is applied for the texture mixing. Within the scope of this thesis, there is also described the application implementation, which enables experimenting with texture creating.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.