Essays about: "psnr"

Showing result 1 - 5 of 40 essays containing the word psnr.

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

    University essay from Lunds universitet/Matematik LTH

    Author : Johan Liljegren; Pontus Nordqvist; [2021]
    Keywords : 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;

    Abstract : 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. READ MORE

  2. 2. Image Processing in MRI Guided Real-TimeAdaptive Radiotheraphy - Upsampling and Segmentation of Target Volume and Organs at Risk

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Shreyas Shivakumara; [2021]
    Keywords : ;

    Abstract : Magnetic Resonance Imaging (MRI) is a useful medical imaging technique that is used for cancer treatment.The major drawback of this method is the relatively long scan time, limiting its use for real time tracking of a potentially moving target during the radiotherapy session. READ MORE

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

    University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknik

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

    Abstract : 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. READ MORE

  4. 4. Upscaling of pictures using convolutional neural networks

    University essay from Uppsala universitet/Avdelningen för visuell information och interaktion; Uppsala universitet/Avdelningen för visuell information och interaktion

    Author : Caspar Norée Palm; Hugo Granström; [2021]
    Keywords : super; resolution; convolutional; neural; networks; upscaling; pictures; psnr; u-net; unet;

    Abstract : The task of upscaling pictures is very ill-posed since it requires the creation of novel data. Any algorithm or model trying to perform this task will have to interpolate and guess the missing pixels in the pictures. Classical algorithms usually result in blurred or pixelated interpolations, especially visible around sharp edges. READ MORE

  5. 5. ARMAS: Active Reconstruction of Missing Audio Segments

    University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Author : Sachin Pokharel; Muhammad Ali; [2021]
    Keywords : Audio Reconstruction; Audio Inpainting; Deep Learning; Machine Learning; Audio Steganography;

    Abstract : Background: Audio signal reconstruction using machine/deep learning algorithms has been explored much more in the recent years, and it has many applications in digital signal processing. There are many research works on audio reconstruction with linear interpolation, phase coding, tone insertion techniques combined with AI models. READ MORE