Super-resolution assessment and detection

Super Resolution (SR) techniques are powerful digital manipulation tools that have significantly impacted various industries due to their ability to enhance the resolution of lower quality images and videos. Yet, the real-world adaptation of SR models poses numerous challenges, which blind SR models...

Descripción completa

Detalles Bibliográficos
Autor: López Cuena, Enrique
Tipo de recurso: tesis de maestría
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/395959
Acceso en línea:https://hdl.handle.net/2117/395959
Access Level:acceso abierto
Palabra clave:Machine learning
Computer vision
aprenentatge automàtic
super-resolució
detecció d'imatges sintètiques
machine learning
superresolution
synthetic image detection
visió per ordinador
computer vision
Aprenentatge automàtic
Visió per ordinador
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Descripción
Sumario:Super Resolution (SR) techniques are powerful digital manipulation tools that have significantly impacted various industries due to their ability to enhance the resolution of lower quality images and videos. Yet, the real-world adaptation of SR models poses numerous challenges, which blind SR models aim to overcome by emulating complex real-world degradations. In this thesis, we investigate these SR techniques, with a particular focus on comparing the performance of blind models to their non-blind counterparts under various conditions. Despite recent progress, the proliferation of SR techniques raises concerns about their potential misuse. These methods can easily manipulate real digital content and create misrepresentations, which highlights the need for robust SR detection mechanisms. In our study, we analyze the limitations of current SR detection techniques and propose a new detection system that exhibits higher performance in discerning real and upscaled videos. Moreover, we conduct several experiments to gain insights into the strengths and weaknesses of the detection models, providing a better understanding of their behavior and limitations. Particularly, we target 4K videos, which are rapidly becoming the standard resolution in various fields such as streaming services, gaming, and content creation. As part of our research, we have created and utilized a unique dataset in 4K resolution, specifically designed to facilitate the investigation of SR techniques and their detection.