Can I read A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only on EtoBox?

A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only by Möller, Björn; Görnhardt, Lucas; Fingscheidt, Tim is a scholarly article available to read on EtoBox.

What is A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only about?

Transformer architectures prominently lead single-image super-resolution (SISR) benchmarks, reconstructing high-resolution (HR) images from their low-resolution (LR) counterparts. Their strong representative power, however, comes with a higher demand for training data compared to convolutional neural networks (CNNs). For many real-world SR applications, the availability of high-quality HR training images is not given, sparking interest in LR-only training methods. The LR-only SISR benchmark mimics this condition by allowing only low-resolution (LR) images for model training. For a 4x super-resolution, this effectively reduces the amount of available training data to 6.25% of the HR image pixels, which puts the employment of a data-hungry transformer model into question. In this work, we are the first to utilize a lightweight vision transformer model with LR-only training methods addressing the unsupervised SISR LR-only benchmark. We adopt and configure a recent LR-only training method from microscopy image super-resolution to macroscopic real-world data, resulting in our multi-scale training method for bicubic degradation (MSTbic). Furthermore, we compare it with reference methods

Author

Möller, Björn; Görnhardt, Lucas; Fingscheidt, Tim

Published

2025

Language

EN