Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such …
Y Tai, J Yang, X Liu, C Xu - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term …
In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real …
Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised …
Y Guo, J Chen, J Wang, Q Chen… - Proceedings of the …, 2020 - openaccess.thecvf.com
Deep neural networks have exhibited promising performance in image super-resolution (SR) by learning a nonlinear mapping function from low-resolution (LR) images to high …
J Zhang, J Huang, M Yao, Z Yang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Learning to leverage the relationship among diverse image restoration tasks is quite beneficial for unraveling the intrinsic ingredients behind the degradation. Recent years have …
Z Du, D Liu, J Liu, J Tang, G Wu… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Runtime and memory consumption are two important aspects for efficient image super- resolution (EISR) models to be deployed on resource-constrained devices. Recent …
Learning continuous image representations is recently gaining popularity for image super- resolution (SR) because of its ability to reconstruct high-resolution images with arbitrary …
Y Cui, W Ren, X Cao, A Knoll - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
Image restoration aims to reconstruct the latent sharp image from its corrupted counterpart. Besides dealing with this long-standing task in the spatial domain, a few approaches seek …