Residual scale attention network for arbitrary scale image super-resolution

Fu, Ying; Chen, Jian; Zhang, Tao; Lin, Yonggang

doi:10.1016/j.neucom.2020.11.010

Cited by 35 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, using a single simple scale information to condition the entire SR network would restrict the performance. The architecture of Meta-SR has been further explored and improved in some subsequent works (e.g., ArbRCAN [48], RSI-HFAS [49], RSAN [50]). They often design a scale parser module to term the magnification factor as a network conditional input, or an upsampling module to dynamically resize the feature map according to the magnification.…”

Section: B Image Sr With Continuous Magnificationmentioning

confidence: 99%

Resolution-Agnostic Remote Sensing Scene Classification With Implicit Neural Representations

Chen

et al. 2023

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable super-resolution framework called FunSR, which settles different magnifications with a unified model by exploiting context interaction within implicit function space. FunSR composes a functional representor, a functional interactor, and a functional parser. Specifically, the representor transforms the low-resolution image from Euclidean space to multi-scale pixel-wise function maps; the interactor enables pixel-wise function expression with global dependencies; and the parser, which is parameterized by the interactor's output, converts the discrete coordinates with additional attributes to RGB values. Extensive experimental results demonstrate that FunSR reports state-of-the-art performance on both fixed-magnification and continuous-magnification settings, meanwhile, it provides many friendly applications thanks to its unified nature.

show abstract

Section: B Image Sr With Continuous Magnificationmentioning

confidence: 99%

Resolution-Agnostic Remote Sensing Scene Classification With Implicit Neural Representations

Chen

et al. 2023

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…The compared models for specific scale factors are DBPN [13], GFSR [19], [54], SAN [55], HAN [56], RCAN [15], NLSA [57], FSDN [25], IPT [17], and EGADNet [12]. The compared models trained for arbitrary scale factors are ASDN [25], Meta-RDN [22], ArbRCAN [28], RSAN [24], LIIF [27], fSISR [30], and RPB [29]. The scale factors considered for comparisons with state-of-the-art models are ×2, ×3, and ×4.…”

Section: B Testing Detailsmentioning

confidence: 99%

“…However, this additional information is not used by the rest of the model, i.e., the backbone parameters of the model are the same for all scale factors for which the model was trained. Fu et al [24] extend the meta module by combining its original linear input vector with a quadratic and a bicubic encoded vector. This approach leads to a higher complexity of the encoding vector as the degree increases with no necessary a better performance of the proposal.…”

Section: Introductionmentioning

confidence: 99%

Arbitrary Scale Super-Resolution Neural Network Based on Residual Channel-Spatial Attention

Gurrola-Ramos

Alarcón²,

Dalmau

2022

IEEE Access

View full text Add to dashboard Cite

In recent years, the performance of convolutional neural networks in single-image superresolution has improved significantly. However, most state-of-the-art models address the super-resolution problem for specific scale factors. In this paper, we propose a convolutional neural network for arbitrary scale super-resolution. Specifically, given a range of scale factors, the proposed model can generate superresolution images with non-integer scale factors within the range. The proposed model incorporates a channel-spatial attention block in which the scale factor is also provided. This module recovers the most relevant information from the low-resolution image given the scale factor and enhances the upsampled image before generating the high-resolution target image. This channel attention block allows learning the channel and spatial dependencies. Additionally, we incorporate global residual learning so that the model recovers the details of an upsampled low-resolution image by interpolation. We evaluated the proposed method through extensive experiments on widely used benchmark datasets for single-image super-resolution. In order to assess the performance of the model, we used the peak signal-to-noise ratio and the structural similarity index measure. The proposed model achieves an average of 35.36, 31.78, 29.62 for peak signalto-noise ratio, and 0.9410, 0.8828, 0.8334 for structural similarity index measure for the standard evaluation scale factors ×2, ×3, ×4, respectively. The experimental results show a better performance of the proposed model over other state-of-the-art models for arbitrary scale super-resolution, and are competitive with models trained for specific scale factors.

show abstract

“…Meta‐SR [HMZ19] applies meta‐learning to predict the weights of filters for different scale factors; however, it does not exploit scale information during feature learning. To solve this problem, the RSAN [YFL21] introduces a residual scale attention network that is employed as prior knowledge to learn discriminative features.…”

Section: Related Workmentioning

confidence: 99%

Ref‐ZSSR: Zero‐Shot Single Image Superresolution with Reference Image

Han

Xue

Wang

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Single image superresolution (SISR) has achieved substantial progress based on deep learning. Many SISR methods acquire pairs of low‐resolution (LR) images from their corresponding high‐resolution (HR) counterparts. Being unsupervised, this kind of method also demands large‐scale training data. However, these paired images and a large amount of training data are difficult to obtain. Recently, several internal, learning‐based methods have been introduced to address this issue. Although requiring a large quantity of training data pairs is solved, the ability to improve the image resolution is limited if only the information of the LR image itself is applied. Therefore, we further expand this kind of approach by using similar HR reference images as prior knowledge to assist the single input image. In this paper, we proposed zero‐shot single image superresolution with a reference image (Ref‐ZSSR). First, we use an unconditional generative model to learn the internal distribution of the HR reference image. Second, a dual‐path architecture that contains a downsampler and an upsampler is introduced to learn the mapping between the input image and its downscaled image. Finally, we combine the reference image learning module and dual‐path architecture module to train a new generative model that can generate a superresolution (SR) image with the details of the HR reference image. Such a design encourages a simple and accurate way to transfer relevant textures from the reference high‐definition (HD) image to LR image. Compared with using only the image itself, the HD feature of the reference image improves the SR performance. In the experiment, we show that the proposed method outperforms previous image‐specific network and internal learning‐based methods.

show abstract

Residual scale attention network for arbitrary scale image super-resolution

Cited by 35 publications

References 44 publications

Resolution-Agnostic Remote Sensing Scene Classification With Implicit Neural Representations

Resolution-Agnostic Remote Sensing Scene Classification With Implicit Neural Representations

Arbitrary Scale Super-Resolution Neural Network Based on Residual Channel-Spatial Attention

Ref‐ZSSR: Zero‐Shot Single Image Superresolution with Reference Image

Contact Info

Product

Resources

About