Abstract / truncated to 115 words (read the full abstract)

Super-resolution (SR) is an ill-posed inverse problem focused on reconstructing high-resolution images from low-resolution counterparts by recovering missing details. Despite advancements, SR faces persistent challenges in generalization, balancing fidelity and perceptual quality, mitigating artifacts, and ensuring trustworthy results. This thesis tackles these issues through innovations in model architecture, loss design, and sample selection. Central to our contributions is the use of wavelet loss, which improve the ability of SR models to distinguish genuine details from artifacts. By leveraging these losses in both GAN-based and transformer-based models, we achieve enhanced fidelity and perceptual quality. Furthermore, we augment transformer architectures with convolutional non-local sparse attention blocks and wavelet-based training, delivering state-of-the-art performance across diverse datasets. For generative ... toggle 20 keywords

super-resolution (sr) – image restoration – wavelet-domain loss – artifact suppression – perception-distortion trade-off – generative adversarial networks (gans) – diffusion models – flow-based models – transformer-based sr – attention mechanisms – frequency-domain learning – difficulty-aware evaluation – trustworthy image generation – vision-language models (vlm) – multi-model fusion – high-frequency detail reconstruction – human-in-the-loop sr – perceptual quality – sample selection – evaluation metrics

Follow @eurasip