<ul><li>A lightweight image super-resolution transformer trained on low-resolution images only has been introduced.</li><li>Transformer architectures in single-image super-resolution (SISR) have a higher demand for training data compared to CNNs.</li><li>This work utilizes a lightweight vision transformer model with LR-only training methods to address the LR-only SISR benchmark.</li><li>The model outperforms state-of-the-art LR-only SISR methods and shows superior performance on benchmark datasets.</li></ul>

A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only

Discover more