Zobrazeno 1 - 10
of 30
pro vyhledávání: '"rekonstrukce obrazu"'
Autor:
Maslowski, Petr
This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of
Externí odkaz:
http://www.nusl.cz/ntk/nusl-449180
Autor:
Le, Hoang Anh
The main goal of this thesis was to increase reconstruction quality of sparse sampled microscopic images by using neural networks. The thesis will cover various approaches for image reconstruction and will also include descriptions of implementations
Externí odkaz:
http://www.nusl.cz/ntk/nusl-445492
Autor:
Ondráček, Pavel
This thesis deals with methods for optimization in image processing. There is described some of optimization techniques and some applications in image processing. There is also described detailed procedure and realization of bee algorithm, genetic al
Externí odkaz:
http://www.nusl.cz/ntk/nusl-442498
Publikováno v:
CSRN.
In this paper we propose a novel approach for reduction of JPEG artifacts using advanced techniques of stochasticcalculus. In order to solve this problem we use backward stochastic differential equations (in short BSDEs) andthe non local means method
Autor:
Trávníčková, Kateřina
This thesis deals with CT data segmentation using convolutional neural nets and describes the problem of training with limited training sets. User interaction is suggested as means of improving segmentation quality for the models trained on small tra
Externí odkaz:
http://www.nusl.cz/ntk/nusl-432864
Autor:
Havelková, Eva
The aim of this thesis is to investigate applicability of regulariza- tion by Krylov subspace methods to discrete inverse problems arising in single particle analysis (SPA). We start with a smooth model formulation and describe its discretization, yi
Externí odkaz:
http://www.nusl.cz/ntk/nusl-393612
Autor:
Šťasta, Jakub
The problem of accurately simulating light transport using Monte Carlo integration can be very difficult. In particular, scenes with complex illumination effects or complex materials can cause a scene to converge very slowly and demand a lot of compu
Externí odkaz:
http://www.nusl.cz/ntk/nusl-368350
Autor:
Kříž, Tomáš
This doctoral thesis proposes a new algorithm for the reconstruction of impedance images in monitored objects. The algorithm eliminates the spatial resolution problems present in existing reconstruction methods, and, with respect to the monitored obj
Externí odkaz:
http://www.nusl.cz/ntk/nusl-234654
We propose a simple and efficient method to reconstruct materials’ bidirectional texture functions (BTFs) from angularly sparse measurements. The key observation is that materials of similar types exhibit both similar surface structure and reflecta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______8936::b53bc426fe82b46a975b5f88568a5fc3
http://hdl.handle.net/11025/11904
http://hdl.handle.net/11025/11904