K. Upla

CEM-TUDASR, a computationally efficient unsupervised Transformer-based super-resolution framework for WCE image enhancement without paired low-resolution (LR) and high-resolution (HR) training data, is proposed.

Representation complexity in Vision Transformers grows through richer transformations while maintaining strong token interactions, reshaping our understanding of model training dynamics.

A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.