Essays about: "superupplösning"

Showing result 1 - 5 of 9 essays containing the word superupplösning.

  1. 1. Generalized super-resolution of 4D Flow MRI : extending capabilities using ensemble learning

    University essay from Linköpings universitet/Institutionen för medicinsk teknik

    Author : Adam Hjalmarsson; Leon Ericsson; [2023]
    Keywords : 4D Flow MRI; Ensemble learning; Super-resolution; Machine learning; Neural networks; 4DFlowNet;

    Abstract : 4D Flow Magnet Resonance Imaging (4D Flow MRI) is a novel non-invasive technique for imaging of cardiovascular blood flow. However, when utilized as a stand-alone analysis method, 4D Flow MRI has certain limitations including limited spatial resolution and noise artefacts, motivating the application of dedicated post-processing tools. READ MORE

  3. 2. Deep learning for temporal super-resolution of 4D Flow MRI

    University essay from KTH/Matematik (Avd.)

    Author : Pia Callmer; [2023]
    Keywords : Temporal super-resolution; 4D Flow MRI; CNN; Artificial Intelligence; MRI; 4D flow; Temporal superupplösning; 4D flöde MRI; CNN; artificiell intelligens; MRI; 4D-flöde;

    Abstract : The accurate assessment of hemodynamics and its parameters play an important role when diagnosing cardiovascular diseases. In this context, 4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique that facilitates hemodynamic parameter assessment as well as quantitative and qualitative analysis of three-directional flow over time. READ MORE

  4. 3. High Resolution Quality Enhancement of Digitized Artwork using Generative Adversarial Networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Dennis Magnusson; [2022]
    Keywords : Image enhancement; Image style transfer; Image superresolution; Machine Learning; Bildförbättring; Bildstilöversättning; Bildsuperupplösning; Maskininlärning;

    Abstract : Digitization of physical artwork is usually done using image scanning devices in order to ensure that the output is accurate in terms of color and is of sufficiently high resolution, usually over 300 pixels per inch, however the usage of such a device is in some cases unfeasible due to medium or size constraints. Photography of the artwork is another method of artwork digitization, however such methods often produce results containing camera artifacts such as shadows, reflections or low resolution. READ MORE

  5. 4. Real-Time Video Super-Resolution : A Comparative Study of Interpolation and Deep Learning Approaches to Upsampling Real-Time Video

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Erik Båvenstrand; [2021]
    Keywords : Super-Resolution; Real-Time; Deep Learning; Upsampling; Computer Vision; Machine Learning; Motion Compensation; Temporal Coherence; Superupplösning; Realtid; Djupinlärning; Uppsampling; Datorseende; Maskininlärning; Rörelsekompensation; Temporalt Sammanhängande;

    Abstract : Super-resolution is a subfield of computer vision centered around upsampling low-resolution images to a corresponding high-resolution counterpart. This degree project investigates the suitability of a deep learning method for real-time video super-resolution. READ MORE

  6. 5. Ensembles of Single Image Super-Resolution Generative Adversarial Networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Victor Castillo Araújo; [2021]
    Keywords : Generative Adversarial Networks; Single Image Super-Resolution; Computer Vision; Convolutional Neural Networks; Ensemble Learning; Generative Adversarial Networks; Superupplösning; Datorseende; Bildanalys; Convolutional neural networks; Ensembler;

    Abstract : Generative Adversarial Networks have been used to obtain state-of-the-art results for low-level computer vision tasks like single image super-resolution, however, they are notoriously difficult to train due to the instability related to the competing minimax framework. Additionally, traditional ensembling mechanisms cannot be effectively applied with these types of networks due to the resources they require at inference time and the complexity of their architectures. READ MORE