Transformer-based networks using attention mechanisms have shown promising results in low-level vision tasks, such as image super-resolution (SR). Specifically, recent studies that utilize window-based self-attention exhibited notable advancements SR. However, self-attention, a slower expansion of the receptive field, thereby restricting modeling long-range dependencies. To address this issue, ...

A robust approach for super resolution is presented, which is especially valuable in the presence of outliers. Such outliers may be due to motion erros, inaccurate blur models, noise, moving objects, motion blur etc. This robustness is needed since super-resolution methods are very sensitive to such errors. A robust median estimator is combined in an iterative process to achieve a super resolut...

This paper presents a wavelet-based computationally efficient implementation of the Linear Minimum Mean Square Error (LMMSE) algorithm in image super-resolution. The image super-resolution reconstruction problem is well-known to be an ill-posed inverse problem of large dimensions. The LMMSE estimator to be implemented in the image super-resolution reconstruction problem requires an inversion of...

Image super-resolution (SR) techniques are used to generate a high-resolution image from low-resolution image. Until now, deep generative models such as autoregressive and Generative Adversarial Networks (GANs) have proven be effective at modelling images. VAE-based often been criticised for their feeble performance, but with new advancements VDVAE, there is now strong evidence that VAEs the po...

Light field (LF) image super-resolution (SR) aims at reconstructing high-resolution LF images from their low-resolution counterparts. Although CNN-based methods have achieved remarkable performance in SR, these cannot fully model the non-local properties of 4D data. In this paper, we propose a simple but effective Transformer-based method for SR. our method, an angular Transformer is designed t...