Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

Li, Wenjie; Li, Juncheng; Gao, Guangwei; Zhou, Jian; Yang, Jian; Qi, Guo-Jun

doi:10.48550/arxiv.2207.02796

Cited by 2 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the proposed DATN with existing SR networks on the BI degradation model: SRCNN, 8 FSRCNN, 3 VDSR, 9 DRCN, 14 LapSRN, 40 DRRN, 15 SelNet, 41 MemNet, 42 SRMDNF, 43 IDN, 17 CARN, 19 CARN-M, 19 SRFBN-S, 44 CBPN, 45 CBPN-S, 45 AWSRN-M, 46 OISR-RK2-s, 47 A2F-S, 21 LESRCNN, 20 SPBP-L, 48 RMUN, 49 FALSR-A, 16 FALSR-B, 16 FALSR-C, 16 WMRN, 50 LMAN-s, 51 MADNet-L1, 52 MSWSR, 13 Cross-SRN, 53 ACNet, 54 CRMBN, 55 DRSAN-48m, 56 AFAN, 57 ESRT, 58 and LBNet. 59…”

Section: Results With Bi Degradationmentioning

confidence: 99%

Dual-aware transformer network for single-image super-resolution

Luo

Wang

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

The advent of deep learning has enabled image super-resolution (SR) technology to achieve tremendous success. The recent exploration between convolutional neural network (CNN) and transformer has produced an impressive performance. However, the huge model size and heavy computational cost occupied by most approaches cannot be ignored. Additionally, the global and local modeling of image features is not well utilized and explored, which is important for texture content reconstruction. In this study, we present an efficient and lightweight network based on CNN and transformer for image SR, dubbed dual-aware transformer network (DATN). Specifically, a dual-aware fusion module (DAFM), consisting of spatial-aware adaptive block (SAAB) and global-aware fusion block (GAFB), learns local and global features in a complementary manner for yielding abundant content details. SAAB delivers the captured spatial information to GAFB in parallel, whereas GAFB establishes long-range spatial dependencies among diverse features to boost the network's ability for recovering texture details. Further, in the upsampling stage, our proposed transformer-empowered upsampling module aggregates global information from the transformer module to generate location-wise reassembly kernels for content-aware upsampling. In such way, feature-rich information is highlighted adaptively to reconstruct high-quality images with maximum efficiency. Experimental results reveal that our proposed DATN achieves high qualitative performance while maintaining low computational demands, surpassing most state-of-the-art SR networks.

show abstract

Section: Results With Bi Degradationmentioning

confidence: 99%

Dual-aware transformer network for single-image super-resolution

Luo

Wang

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Hybrid network of CNN and Transformer (HNCT) 12 combined CNN and Transformer to extract deep features in consideration of both local and non-local priors. Similarly, cross-receptive focused inference network (CFIN) 13 elegantly integrated CNN and Transformer and achieved competitive performance. In aggregate enriched features extracted from both CNN and Transformer (ACT) 14 , it exploited multi-scale local and non-local attributes to improve SR quality.…”

mentioning

confidence: 99%

Lightweight interactive feature inference network for single-image super-resolution

Wang,

Li,

Tian

et al. 2024

Sci Rep

View full text Add to dashboard Cite

The emergence of convolutional neural network (CNN) and transformer has recently facilitated significant advances in image super-resolution (SR) tasks. However, these networks commonly construct complex structures, having huge model parameters and high computational costs, to boost reconstruction performance. In addition, they do not consider the structural prior well, which is not conducive to high-quality image reconstruction. In this work, we devise a lightweight interactive feature inference network (IFIN), complementing the strengths of CNN and Transformer, for effective image SR reconstruction. Specifically, the interactive feature aggregation module (IFAM), implemented by structure-aware attention block (SAAB), Swin Transformer block (SWTB), and enhanced spatial adaptive block (ESAB), serves as the network backbone, progressively extracts more dedicated features to facilitate the reconstruction of high-frequency details in the image. SAAB adaptively recalibrates local salient structural information, and SWTB effectively captures rich global information. Further, ESAB synergetically complements local and global priors to ensure the consistent fusion of diverse features, achieving high-quality reconstruction of images. Comprehensive experiments reveal that our proposed networks attain state-of-the-art reconstruction accuracy on benchmark datasets while maintaining low computational demands. Our code and results are available at: https://github.com/wwaannggllii/IFIN.

show abstract

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

Cited by 2 publications

References 43 publications

Dual-aware transformer network for single-image super-resolution

Dual-aware transformer network for single-image super-resolution

Lightweight interactive feature inference network for single-image super-resolution

Contact Info

Product

Resources

About