South-Central Minzu University,a. College of Electronic and Information Engineering; b. Hubei Key Lab of Intelligent Wireless Communication; c. College of Computer Science,Wuhan 430074,Hubei China
Infrared image super-resolution has wide applications. Currently, the Visual Transformer has shown great potential in improving the performance of image super-resolution, but how to effectively balance system complexity has attracted the interest of many researchers. A random permutation based Transformer for infrared image super-resolution is proposed, which achieves further improvement in image reconstruction performance while controlling system complexity well. Specifically, a window self-attention module combining random permutation is designed to replace the original Swin Transformer's shifted window self-attention module, effectively improving the learning ability of global dependency relationships of window self-attention through random permutation operations in the spatial dimension of the feature map. Experimental comparison results based on multiple public infrared image datasets validate the effectiveness of this method.
WangC, LiX. Infrared image feature analysis and application in the field of image encryption[C]//2021 IEEE 4th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). Shenyang: IEEE, 2021: 578-583.
[2]
DanaciK I, AkagunduzE. A survey on infrared image & video sets[J]. Multimedia Tools and Applications, 2023, 83(6): 16485-16523.
[3]
WangZ, ChenJ, HoiS C H. Deep learning for image super-resolution: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3365-3387.
[4]
ZhangL, ZhangH, ShenH, et al. A super-resolution reconstruction algorithm for surveillance images[J]. Signal Processing, 2010, 90(3): 848-859.
[5]
TehI, McclymoutD, CarruthE, et al. Improved compressed sensing and super-resolution of cardiac diffusion MRI with structure-guided total variation[J]. Magnetic Resonance in Medicine, 2020, 84(4): 1868-1880.
[6]
HeZ, TangS, YangJ, et al. Cascaded deep networks with multiple receptive fields for infrared image super-resolution[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(8): 2310-2322.
[7]
HanT Y, KimY J, SongB C. Convolutional neural network-based infrared image super resolution under low light environment[C]//2017 25th European Signal Processing Conference (EUSIPCO). Kos: IEEE, 2017: 803-807.
[8]
DuJ, ZhouH, QianK, et al. RGB-IR cross input and sub-pixel upsampling network for infrared image super-resolution[J]. Sensors, 2020, 20(1): 281.
[9]
LiangS, SongK, ZhaoW, et al. DASR: Dual-Attention Transformer for infrared image super-resolution[J]. Infrared Physics & Technology, 2023, 133: 104837.
[10]
VaswaniA, ShazeerN, ParmarN, et al. Attention is All you Need [J]. Advances in Neural Information Processing Systems, 2017:30.
[11]
LiuZ, LinY, CaoY, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal: IEEE, 2021: 9992-10002.
[12]
LiangJ, CaoJ, SunG, et al. SwinIR: Image restoration using swin transformer[C]//2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Montreal: IEEE, 2021: 1833-1844.
[13]
ZhangJ, ZhangY, GuJ, et al. Accurate image restoration with attention retractable transformer[C]//International Conference on Learning Representations. Kigali: ICLR, 2023: 1-13.
[14]
ZhengL, ZhuJ, ShiJ, et al. Efficient mixed transformer for single image super-resolution[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108035.
[15]
XiaoJ, FuX, ZhouM, et al. Random shuffle transformer for image restoration[C]//Proceedings of the 40th International Conference on Machine Learning. Honolulu: ACM, 2023: 38039-38058.
[16]
ShiW, CaballeroJ, HuszarF, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 1874-1883.
[17]
AgustssonE, TimofteR. NTIRE 2017 challenge on single image super-resolution: Dataset and Study[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu: IEEE, 2017: 1122-1131.
[18]
HuangY, JiangZ, LanR, et al. Infrared image super-resolution via transfer learning and PSRGAN[J]. IEEE Signal Processing Letters, 2021, 28: 982-986.
[19]
RivadeneiraR E, SuárezP L, SappaA D, et al. Thermal image SuperResolution through deep convolutional neural network[C]//International Conference on Image Analysis and Recognition. Waterloo: ICIAR, 2019: 417-426.
[20]
DongC, LoyC C, HeK, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(2): 295-307.
[21]
LimB, SonS, KimH, et al. Enhanced deep residual networks for single image super-resolution[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu: IEEE, 2017: 1132-1140.