PuSH - Publication Server of Helmholtz Zentrum München

Umer, R.M. ; Micheloni, C.*

Real image super-resolution using GAN through modeling of LR and HR process.

In: (AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance, 29 November- 02 December 2022, Madrid, Spain). 2022. DOI: 10.1109/AVSS56176.2022.9959415 (AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance)
DOI
The current existing deep image super-resolution methods usually assume that a Low Resolution (LR) image is bicubicly downscaled of a High Resolution (HR) image. However, such an ideal bicubic downsampling process is different from the real LR degradations, which usually come from complicated combinations of different degradation processes, such as camera blur, sensor noise, sharpening artifacts, JPEG compression, and further image editing, and several times image transmission over the internet and unpredictable noises. It leads to the highly ill-posed nature of the inverse upscaling problem. To address these issues, we propose a GAN-based SR approach with learnable adaptive sinusoidal nonlinearities incorporated in LR and SR models by directly learn degradation distributions and then synthesize paired LR/HR training data to train the generalized SR model to real image degradations. We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Conference Title AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance
Conference Date 29 November- 02 December 2022
Conference Location Madrid, Spain
Non-patent literature Publications
Institute(s) Institute of Computational Biology (ICB)