Sökning: "Structural Similarity Index Measure"

Visar resultat 1 - 5 av 8 uppsatser innehållade orden Structural Similarity Index Measure.

  1. 1. Deep Learning-based Regularizers for Cone Beam Computed Tomography Reconstruction

    Master-uppsats, KTH/Matematisk statistik

    Författare :Sabina Syed; Josefin Stenberg; [2023]
    Nyckelord :Adversarial Convex Regularization; Computer Vision; Cone Beam Computed Tomography; Convolutional Neural Networks; Deep Learning; Image Reconstruction; Adversarial Convex Regularization; Bildrekonstruktion; Datorseende; Djupinlärning; Faltningsnätverk; Volymtomografi;

    Sammanfattning : Cone Beam Computed Tomography is a technology to visualize the 3D interior anatomy of a patient. It is important for image-guided radiation therapy in cancer treatment. During a scan, iterative methods are often used for the image reconstruction step. LÄS MER

  3. 2. The Speed of Clouds : Utilizing Adaptive Sampling to Optimize a Real-Time Volumetric Cloud Renderer

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Emrik Hydén; [2023]
    Nyckelord :Volumetric clouds; Ray marching; Bilinear interpolation; Adaptive sampling; Unity3D; Volymetriska moln; Ray marching; Bilinjär interpolering; Adaptiv sampling; Unity3D;

    Sammanfattning : Volumetric clouds are often used in video games in order to improve the realism or graphical quality of the game. However, in order to achieve real-time rendered clouds, optimizations have to be implemented as part of the rendering algorithm. LÄS MER

  4. 3. Unsupervised Image-to-image translation : Taking inspiration from human perception

    Magister-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Jens Jakob Sveding; [2021]
    Nyckelord :Artificial intelligence; Unsupervised learning; Image-to-Image translation; Generative Adversarial Networks; Structural Similarity Index Measure;

    Sammanfattning : Generative Artificial Intelligence is a field of artificial intelligence where systems can learn underlying patterns in previously seen content and generate new content. This thesis explores a generative artificial intelligence technique used for image-toimage translations called Cycle-consistent Adversarial network (CycleGAN), which can translate images from one domain into another. LÄS MER

  5. 4. Deep Learning based Video Super- Resolution in Computer Generated Graphics

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Vinit Jain; [2020]
    Nyckelord :Deep Learning; Convolutional Neural Networks; Video Super-Resolution; Computer Generated Graphics; Gaming.; Deep Learning; Convolutional Neural Networks; Video Super-Resolution; Computer Generated Graphics; Gaming.;

    Sammanfattning : Super-Resolution is a widely studied problem in the field of computer vision, where the purpose is to increase the resolution of, or super-resolve, image data. In Video Super-Resolution, maintaining temporal coherence for consecutive video frames requires fusing information from multiple frames to super-resolve one frame. LÄS MER

  7. 5. Reducing the pixelated look of Variable Rate Shading on particle effects

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Joakim Lilja; [2020]
    Nyckelord :;

    Sammanfattning : As video games get more and more demanding and screen resolutions continue to increase, new methods to render video games at high frame rates are needed. Variable Rate Shading is a technique currently available on Nvidia’s Turing architecture and Intel Gen11 hardware. LÄS MER