Sökning: "FID-Score"

Visar resultat 1 - 5 av 6 uppsatser innehållade ordet FID-Score.

  1. 1. Generating Synthetic CT Images Using Diffusion Models

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Salih Saleh; [2023]
    Nyckelord :Machine learning; artificial intelligence; generative models; diffusion models; MRI; CT; synthetic CT; radiation therapy;

    Sammanfattning : Magnetic resonance (MR) images together with computed tomography (CT) images are used in many medical practices, such as radiation therapy. To capture those images, patients have to undergo two separate scans: one for the MR image, which involves using strong magnetic fields, and one for the CT image which involves using radiation (x-rays). LÄS MER

  3. 2. Fingerprint Synthesis Using Deep Generative Models

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Weizhong Tang; Diego André Figueroa Llamosas; [2023]
    Nyckelord :Fingerprint Synthesis; Deep Generative Models; Style Transfer; Metrics; Technology and Engineering;

    Sammanfattning : The advancements in biometric technology have amplified the need for more robust fingerprint synthesis techniques. In this thesis, we first explored the application of synthesizing normal fingerprint images in high fidelity using deep generative models (e.g. LÄS MER

  4. 3. Analyzing the Negative Log-Likelihood Loss in Generative Modeling

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

    Författare :Aleix Espuña I Fontcuberta; [2022]
    Nyckelord :Generative modeling; Normalizing flows; Generative Adversarial Networks; MaximumLikelihood Estimation; Real Non-Volume Preserving flow; Fréchet Inception Distance; Misspecification; Generativa metoder; Normalizing flows; Generative adversarial networks; Maximum likelihood-metoden; Real non-volume preserving flow; Fréchet inception distance; felspecificerade modeller;

    Sammanfattning : Maximum-Likelihood Estimation (MLE) is a classic model-fitting method from probability theory. However, it has been argued repeatedly that MLE is inappropriate for synthesis applications, since its priorities are at odds with important principles of human perception, and that, e.g. LÄS MER

  5. 4. Generative Adversarial Networks in Lip-Synchronized Deepfakes for Personalized Video Messages

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Johan Liljegren; Pontus Nordqvist; [2021]
    Nyckelord :Generative Adversarial Networks; GAN; Lip-Synchronization; Deepfake; Deep Learning; Autoencoder; WGAN; WGAN-GP; L1WGAN-GP; Skip-Connections; FID-Score; Mathematics and Statistics; Technology and Engineering;

    Sammanfattning : The recent progress of deep learning has enabled more powerful frameworks to create good-quality deepfakes. Deepfakes, which are mostly known for malicious purposes, have great potential to be useful in areas such as the movie industry, education, and personalized messaging. LÄS MER

  7. 5. AI-Driven Image Manipulation : Image Outpainting Applied on Fashion Images

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Alexander Mennborg; [2021]
    Nyckelord :image outpainting; fashion images; product images; image cropping; image resizing; convolutional neural networks; generative adversarial networks;

    Sammanfattning : The e-commerce industry frequently has to deal with displaying product images in a website where the images are provided by the selling partners. The images in question can have drastically different aspect ratios and resolutions which makes it harder to present them while maintaining a coherent user experience. LÄS MER