Deep convolutional networks–based super-resolution is a fast-growing field with numerous practical applications. In this exposition, we extensively compare more than 30 state-of-the …
Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for …
Image restoration is a long-standing low-level vision problem that aims to restore high- quality images from low-quality images (eg, downscaled, noisy and compressed images) …
Previous works have shown that increasing the window size for Transformer-based image super-resolution models (eg, SwinIR) can significantly improve the model performance but …
Y Mei, Y Fan, Y Zhou - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Both non-local (NL) operation and sparse representation are crucial for Single Image Super- Resolution (SISR). In this paper, we investigate their combinations and propose a novel Non …
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems. Such a …
B Niu, W Wen, W Ren, X Zhang, L Yang… - Computer Vision–ECCV …, 2020 - Springer
Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in …
RQ Wu, ZP Duan, CL Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Existing dehazing approaches struggle to process real-world hazy images owing to the lack of paired real data and robust priors. In this work, we present a new paradigm for real image …
Compression plays an important role on the efficient transmission and storage of images and videos through band-limited systems such as streaming services, virtual reality or …