|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM379099500 |
| 003 |
DE-627 |
| 005 |
20241028232326.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
241019s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3477350
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1583.xml
|
| 035 |
|
|
|a (DE-627)NLM379099500
|
| 035 |
|
|
|a (NLM)39423089
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wu, Gang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Transforming Image Super-Resolution
|b A ConvFormer-Based Efficient Approach
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 28.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Recent progress in single-image super-resolution (SISR) has achieved remarkable performance, yet the computational costs of these methods remain a challenge for deployment on resource-constrained devices. In particular, transformer-based methods, which leverage self-attention mechanisms, have led to significant breakthroughs but also introduce substantial computational costs. To tackle this issue, we introduce the Convolutional Transformer layer (ConvFormer) and propose a ConvFormer-based Super-Resolution network (CFSR), offering an effective and efficient solution for lightweight image super-resolution. The proposed method inherits the advantages of both convolution-based and transformer-based approaches. Specifically, CFSR utilizes large kernel convolutions as a feature mixer to replace the self-attention module, efficiently modeling long-range dependencies and extensive receptive fields with minimal computational overhead. Furthermore, we propose an edge-preserving feed-forward network (EFN) designed to achieve local feature aggregation while effectively preserving high-frequency information. Extensive experiments demonstrate that CFSR strikes an optimal balance between computational cost and performance compared to existing lightweight SR methods. When benchmarked against state-of-the-art methods such as ShuffleMixer, the proposed CFSR achieves a gain of 0.39 dB on the Urban100 dataset for the x2 super-resolution task while requiring 26% and 31% fewer parameters and FLOPs, respectively. The code and pre-trained models are available at https://github.com/Aitical/CFSR
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Jiang, Junjun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jiang, Junpeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Xianming
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 33(2024) vom: 28., Seite 6071-6082
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:28
|g pages:6071-6082
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3477350
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 33
|j 2024
|b 28
|h 6071-6082
|