Zugl.: Passau, Univ., Diss., 2008

Sketch-to-photo synthesis usually faced the problem of lack of labeled data, so we propose some methods based on CycleGAN to train a model to translate sketch to photo with unpaired data. Our main contribution is a proposed Sketch-to-Skeleton-to-Image (SSI) method, which performs skeletonization on sketches to reduce variance on the sketch data. We also tried different representations of the skeleton and different models for our task. Experiment results show that the generated image quality has a negative correlation with the sparsity of the input data.

The field of computer graphics has made significant progress over the years, transforming from simple, pixelated images to highly realistic visuals used across various industries including entertainment, fashion, and video gaming. However, the traditional process of rendering images remains complex and time-consuming, requiring a deep understanding of geometry, materials, and textures. This thesis introduces a simpler approach through a machine learning model, specifically using Cycle-Consistent Adversarial Networks (CycleGAN), to generate realistic images and estimate global illumination in real-time, significantly reducing the need for extensive expertise and time investment. Our experiments on the Blender and Portal datasets demonstrate the model's ability to efficiently generate high-quality, globally illuminated scenes, while a comparative study with the Pix2Pix model highlights our approach's strengths in preserving fine visual details. Despite these advancements, we acknowledge the limitations posed by hardware constraints and dataset diversity, pointing towards areas for future improvement and exploration. This work aims to simplify the complex world of computer graphics, making it more accessible and user-friendly, while maintaining high standards of visual realism. / Master of Science / Creating realistic images on a computer is a crucial part of making video games and movies more immersive and lifelike. Traditionally, this has been a complex and time-consuming task, requiring a deep understanding of how light interacts with objects to create shadows and highlights. This study introduces a simpler and quicker method using a type of smart computer program that learns from examples. This program, known as Cycle-Consistent Adversarial Networks (CycleGAN), is designed to understand the complex play of light in virtual scenes and recreate it in a way that makes the image look real. In testing this new method on different types of images, from simpler scenes to more complex ones, the results were impressive. The program was not only able to significantly cut down the time needed to render an image, but it also maintained the fine details that bring an image to life. While there were challenges, such as working with limited computer power and needing a wider variety of images for the program to learn from, the study shows great promise. It represents a big step forward in making the creation of high-quality, realistic computer graphics more accessible and achievable for a wider range of applications.

In the thesis, we aimed at building a robust UAV(drone) detection algorithm through which, one drone could detect another drone in flight. Though this was a straight forward object detection problem, the biggest challenge we faced for drone detection is the limited amount of drone images for training. To address this issue, we used Generative Adversarial Networks, CycleGAN to be precise, for the generation of realistic looking fake images which were indistinguishable from real data. CycleGAN is a classic example of Image to Image Translation technique, and we this applied in our situation where synthetic images from one domain were transformed into another domain, containing real data. The model, once trained, was capable of generating realistic looking images from synthetic data without the presence of real images. Following this, we employed a state of the art object detection model, YOLO(You Only Look Once), to build a Drone Detection model that was trained on the generated images. Finally, the performance of this model was compared against different datasets in order to evaluate its performance. / Master of Science / In the recent years, technologies like Deep Learning and Machine Learning have seen many rapid developments. Among the many applications they have, object detection is one of the widely used application and well established problems. In our thesis, we deal with a scenario where we have a swarm of drones and our aim is for one drone to recognize another drone in its field of vision. As there was no drone image dataset readily available, we explored different ways of generating realistic data to address this issue. Finally, we proposed a solution to generate realistic images using Deep Learning techniques and trained an object detection model on it where we evaluated how well it has performed against other models.

Industry 4.0 imposes strict requirements on Fifth Generation (5G) system, such as high reliability, availability, and low latency. Guaranteeing such requirements means that there are supposed to be a low number of system failures. Such rareness can cause problems when access to a broader range of these failures is necessary (e.g., finding optimal scheduler or learning in Deep Reinforcement Learning (DRL)). This work will investigate the possibility of using Generative Adversarial Network (GAN) to generate rare events in wireless communication data that might cause failure events. Conventional training methods fall short when trained on such a dataset, as they will overfit the common values while ignoring the rare values. We propose an alternative training method for GANs, called incremental learning, that aims at increasing learning in the rare sections without sacrificing the learning of the rest of the dataset. / Industry 4.0 ställer strikta krav på 5Gsystemet, såsom hög tillförlitlighet, tillgänglighet och låg latens. För att säkerställa uppfyllandet av kraven ovan på systemet, måste antalet systemfel vara sällsynta. I vissa fall som t.ex. skapandet av en optimal ”scheduler” eller inlärning av DRL kan det vara problematiskt att ha ett system med sällsynta systemfel. Detta är sant, eftersom det kommer att vara nödvändigt och nästintill ett krav att ha tillgång till ett brett utbud av systemfel. Denna studie kommer undersöka möjligheten att använda GAN för att generera sällsynta händelser i trådlös kommunikationsdata. Konventionell träning misslyckas när den tränas på en sådan datamängd, eftersom den kommer att vara överanpassad för de vanliga värdena samtidigt som de sällsynta värdena ignoreras. Vårt förslag är att använda en så kallad ”incremental learning” som en alternativ metod för GANs. Inom ”incremental learning” strävar man efter att öka inlärningen i de sällsynta fallen utan att offra inlärningen av de resterande datamängd.

We propose an e cient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs. Taking the StyleGAN trained on the FFHQ dataset as an example, we show results for image morphing, style transfer, and expression transfer. Studying the results of the embedding algorithm provides valuable insights into the structure of the StyleGAN latent space. We propose a set of experiments to test what class of images can be embedded, how they are embedded, what latent space is suitable for embedding, and if the embedding is semantically meaningful.

Three-dimensional modeling is the process of creating a representation of a surface or object in three dimensions via a specialized software where the modeler scans a real-world object into a point cloud, creates a completely new surface or edits the selected representation. This process can be challenging due to factors like the complexity of the 3D creation software or the number of dimensions in play. This work proposes a framework that recommends three types of reconstructions of an incomplete or rough 3D model using Generative AdversarialNetworks (GANs). These reconstructions follow the distribution of real data, resemble the user model and stay close to the dataset while keeping features of the input, respectively. The main advantage of this approach is the acceptance of 3Dmodels as input for the GAN instead of latent vectors, which prevents the need of training an extra network to project the model into the latent space. The systems are evaluated both quantitatively and qualitatively. The quantitative measure lies upon the Intersection over Union (IoU) metric while the quantitative evaluation is measured by a user study. Experiments show that it is hard to create a system that generates realistic models, following the distribution of the dataset, since users have different opinions on what is realistic. However, similarity between the user input and the reconstruction is well accomplished and, in fact, the most valued feature for modelers. / Tredimensionell modellering är processen att skapa en representation av en yta eller ett objekt i tre dimensioner via en specialiserad programvara där modelleraren skannar ett verkligt objekt i ett punktmoln, skapar en helt ny yta eller redigerar den valda representationen. Denna process kan vara utmanande på grund av faktorer som komplexiteten i den 3D-skapande programvaran eller antalet dimensioner i spel. I det här arbetet föreslås ett ramverk som rekommenderar tre typer av rekonstruktioner av en ofullständig eller grov 3D-modell med Generative Adversarial Networks (GAN). Dessa rekonstruktioner följer distributionen av reella data, liknar användarmodellen och håller sig nära datasetet medan respektive egenskaper av ingången behålls. Den främsta fördelen med detta tillvägagångssätt är acceptansen av 3D-modeller som input för GAN istället för latentavektorer, vilket förhindrar behovet av att träna ett extra nätverk för att projicera modellen i latent rymd. Systemen utvärderas både kvantitativt och kvalitativt. Den kvantitativa åtgärden beror på Intersection over Union (IoU) metrisk medan den kvantitativa utvärderingen mäts av en användarstudie. Experiment visar att det är svårt att skapa ett system som genererar realistiska modeller efter distributionen av datasetet, eftersom användarna har olika åsikter om vad som är realistiskt. Likvärdighet mellan användarinmatning och rekonstruktion är väl genomförd och i själva verket den mest uppskattade funktionen för modellerare.

This paper aims to investigate how Helsingborg’s city library’s visi-tors feel about computer games being available for lending and in which way computer gamers see Helsingborg’s city library as a resource. This was examined first with a study of 100 of the library’s visitors and then with five interviews with computer gamers and an interview with the librarian responsible for purchasing games.The study showed that most visitors were neutral to having games at the library and of the ones that were not neutral many more were positive than negative. Of the five gamers who were inter-viewed, there were several who had borrowed games in the past. Although all the gamers appre-ciated the opportunity of games at the library, they did not see the library as an obvious resource.The conclusion of the study is that computer games are an appreciated opportunity that can tempt new visitors to the library and that games can renew the library’s offerings and profile. / Program: Bibliotekarie

The area of particle characterization is expansive; it contains many technologies and methods of analysis. Light spectroscopy techniques yield information on the joint property distribution of particles, comprising the chemical composition, size, shape, and orientation of the particles. The objective of this dissertation is to develop a hybrid scattering-absorption model incorporating Mie and Rayleigh-Debye-Gans theory to characterize submicron particles in suspension with multiwavelength spectroscopy.Rayleigh-Debye-Gans theory (RDG) was chosen as a model to relate the particles joint property distribution to the light scattering and absorption phenomena for submicron particles. A correction model to instrument parameters of relevance was implemented to Rayleigh-Debye-Gans theory for spheres. Behavior of nonspherical particles using RDG theory was compared with Mie theory (as a reference). A multiwavelength assessment of Rayleigh-Debye-Gans theory for spheres was conducted where strict adherence to the limits could not be followed. Reported corrections to the refractive indices were implemented to RDG to try and achieve Mies spectral prediction for spheres.The results of studies conducted for RDG concluded the following. The angle of acceptance plays an important role in being able to assess and interpret spectral differences. Multiwavelength transmission spectra contains qualitative information on shape and orientation of non-spherical particles, and it should be possible to extract this information from carefully measured spectra. There is disagreement between Rayleigh-Debye-Gans and Mie theory for transmission simulations with spherical scatterers of different sizes and refractive indices.

This graduation thesis deals with conflicts of regional rock scene with official cultural politics before 1989. The text consists of two large sections, whereas the first one discusses a broader background of the topic and the second one focuses on the problems of rock scene in České Budějovice. Social and political situation during communist regime is reminded at the beginning of dissertation. Following part brings information about development of rock music in the world and Czechoslovakia as well. Some conflicts of rock musicians with the official cultural politics are mentioned here as well, both in nationwide and regional context. The next chapters are based on interviews with witnesses and their recollections of rock scene in České Budějovice before 1989. The last third of the text pays attention to particular problems of this scene. There are mentioned not just minor difficulties, but also bans on music groups, brutal police attack against participants of underground music concert in Rudolfov in 1974 and unfair law suit with Jiří Gans (local jazz and rock music devotee).