Sökning: "ESRGAN"

Hittade 4 uppsatser innehållade ordet ESRGAN.

  1. 1. The influence of neural network-based image enhancements on object detection

    Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

    Författare :Eric Pettersson; Muhammed Al Khayyat; [2023]
    Nyckelord :Object detection; YOLO; image enhancement; ESRGAN; Zero-DCE;

    Sammanfattning : This thesis investigates the impact of image enhancement techniques on object detection for carsin real-world traffic scenarios. The study focuses on upscaling and light correction treatments andtheir effects on detecting cars in challenging conditions. Initially, a YOLOv8x model is trained on clear static car images. LÄS MER

  3. 2. Improving Unreal Engine Imagery using Generative Adversarial Networks

    Master-uppsats, Linköpings universitet/Programvara och system

    Författare :Erik Jareman; Ludvig Knast; [2023]
    Nyckelord :GAN; Generative Adversarial Networks; Unreal Engine; Real-ESRGAN; super resolution; image enhancement;

    Sammanfattning : Game engines such as Unreal Engine 5 are widely used to create photo-realistic renderings. To run these renderings at high quality without experiencing any performance issues,high-performance hardware is often required. LÄS MER

  4. 3. Virtual Staining of Blood Cells using Point Light Source Illumination and Deep Learning

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Joel Wulff; [2022]
    Nyckelord :Deep learning; virtual staining; blood; cells; GANs; Generative adversarial networks; CNNs; convolutional neural networks; ESRGAN; Unet; digital microscopy; Mathematics and Statistics;

    Sammanfattning : Blood tests are an important part of modern medicine, and are essentially always stained using chemical colorization methods before analysis by computational or manual methods. The staining process allows different parts of blood cells to be discerned that would be unnoticeable in unstained blood. LÄS MER

  5. 4. Social Distancing AI: Using super-resolution to train an object detection model on low resolution images

    Kandidat-uppsats, Lunds universitet/Matematisk statistik

    Författare :Dennis Hein; [2020]
    Nyckelord :Mathematics and Statistics;

    Sammanfattning : This paper addresses the following hypothetical situation: suppose that we want to train an object detection algorithm but that only low resolution data is available. As a tentative solution to this problem, this paper suggest to first super-resolve the low resolution data to obtain higher resolution data that is then fed to the object detection algorithm. LÄS MER