IEF-CSNET: Information Enhancement and Fusion Network for Compressed Sensing Reconstruction
Abstract
:1. Introduction
- Based on the Compressed Information Extension (CIE) module, information in the compressed domain is fully utilized for high-dimensional fusion, greatly expanding the receptive field of DNN methods.
- In consideration of the initial image and the error enhancement image recovered by previous iterations, the Error Comprehensive Consideration Enhancement (ECCE) module can incorporate the enhancement information into the output flow more efficiently.
- To solve the information compression due to obtaining errors, an Iterative Information Flow Enhancement (IIFE) module is proposed to complete iterative and progressive recovery during loss-less information transmission.
- Combined with CIE, ECCE, and IIFE, the IEF-CSNET is proposed. On this basis, several experiments and visual analyses of its effectiveness are performed. Under all test sets and sampling rates, the average increase is approximately 0.59 dB, and the operating speed is improved by orders of magnitude from the state-of-the-art (SOTA) method.
2. Related Works
2.1. Compressed Sensing and Traditional Methods
2.2. Deep Learning Methods
3. Methods
3.1. Overview of Proposed Method
- The CIE module expands and integrates the information elements in the compressed domain to output and the Compressed-domain Fusion Error Image , which can take greater advantage of the measurements in each iteration and achieve a larger receptive field (Section 3.2).
- The ECCE module outputs the Enhanced Error Image by taking , , and of the previous iterations into consideration. In this way, the error and residual can be accurately predicted with high robustness to supplement the following reconstruction more efficiently (Section 3.3).
- Based on the IIFE module, the Intermediate Features and can be supplemented progressively and fused more smoothly under loss-less information transmission while the sampling is repeated in the iterative reconstruction process (Section 3.4).
Algorithm 1 Prediction of IEF-CSNET. |
|
3.2. Compressed Information Extension (CIE)
3.3. Error Comprehensive Consideration Enhancement (ECCE)
3.4. Iterative Information Flow Enhancement Module (IIFE)
4. Experiment
4.1. Settings
4.2. Quantitative Evaluation
4.3. Qualitative Evaluation
4.4. Inference Speed
4.5. Ablation Experiment
- IIFE: No IIFE is set, but ECCE, CIE, and the base model in Figure 6 are a part of the network.
- ECCE: No ECCE works, but the other two modules are employed.
- CIE: No CIE is added, but the other two are considered.
- ALL: CIE, ECCE, and IIFE act with united strength.
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Donoho, D. Compressed sensing. IEEE Trans. Inf. Theory 2006, 52, 1289–1306. [Google Scholar] [CrossRef]
- Shannon, C. Communication in the Presence of Noise. Proc. IRE 1949, 37, 10–21. [Google Scholar] [CrossRef]
- Ye, D.; Ni, Z.; Wang, H.; Zhang, J.; Wang, S.; Kwong, S. CSformer: Bridging Convolution and Transformer for Compressive Sensing. arXiv 2021, arXiv:2112.15299. [Google Scholar]
- Zhang, Z.; Liu, Y.; Liu, J.; Wen, F.; Zhu, C. AMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing. IEEE Trans. Image Process. 2021, 30, 1487–1500. [Google Scholar] [CrossRef] [PubMed]
- Liang, J.; Peng, H.; Li, L.; Tong, F. Construction of Structured Random Measurement Matrices in Semi-Tensor Product Compressed Sensing Based on Combinatorial Designs. Sensors 2022, 22, 8260. [Google Scholar] [CrossRef] [PubMed]
- Chen, S.S.; Donoho, D.L.; Saunders, M.A. Atomic decomposition by basis pursuit. SIAM Rev. 2001, 43, 129–159. [Google Scholar] [CrossRef]
- Mallat, S.G.; Zhang, Z. Matching pursuits with time-frequency dictionaries. IEEE Trans. Signal Process. 1993, 41, 3397–3415. [Google Scholar] [CrossRef]
- Tropp, J.A.; Gilbert, A.C. Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans. Inf. Theory 2007, 53, 4655–4666. [Google Scholar] [CrossRef]
- Donoho, D.L.; Tsaig, Y.; Drori, I.; Starck, J.L. Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit. IEEE Trans. Inf. Theory 2012, 58, 1094–1121. [Google Scholar] [CrossRef]
- Shi, W.; Jiang, F.; Zhang, S.; Zhao, D. Deep networks for compressed image sensing. In Proceedings of the 2017 IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, China, 10–14 July 2017; pp. 877–882. [Google Scholar]
- Mun, S.; Fowler, J.E. Residual reconstruction for block-based compressed sensing of video. In Proceedings of the 2011 Data Compression Conference, Palinuro, Italy, 21–24 June 2011; pp. 183–192. [Google Scholar]
- Haupt, J.; Nowak, R. Signal reconstruction from noisy random projections. IEEE Trans. Inf. Theory 2006, 52, 4036–4048. [Google Scholar] [CrossRef]
- Chen, C.; Tramel, E.W.; Fowler, J.E. Compressed-sensing recovery of images and video using multihypothesis predictions. In Proceedings of the 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR), Pacific Grove, CA, USA, 6–9 November 2011; pp. 1193–1198. [Google Scholar]
- Gan, L. Block compressed sensing of natural images. In Proceedings of the 2007 15th International Conference on Digital Signal Processing, Cardiff, UK, 1–4 July 2007; pp. 403–406. [Google Scholar]
- Bertero, M.; Boccacci, P.; De Mol, C. Introduction to Inverse Problems in Imaging; CRC Press: Boca Raton, FL, USA, 2021. [Google Scholar]
- Chengbo Li, W.Y.; Zhang, Y. TVAL3: TV Minimization by Augmented Lagrangian and Alternating Direction Agorithm 2009. 2013. Available online: https://nuit-blanche.blogspot.com/2009/06/cs-tval3-tv-minimization-by-augmented.html (accessed on 19 June 2009).
- Huang, Y.; Li, H.; Peng, J. A Non-Convex Compressed Sensing Model Improving the Energy Efficiency of WSNs for Abnormal Events’ Monitoring. Sensors 2022, 22, 8378. [Google Scholar] [CrossRef]
- Wang, Z.; Gao, Y.; Duan, X.; Cao, J. Adaptive High-Resolution Imaging Method Based on Compressive Sensing. Sensors 2022, 22, 8848. [Google Scholar] [CrossRef]
- Guruprasad, S.; Bharathi, S.; Delvi, D.A.R. Effective compressed sensing MRI reconstruction via hybrid GSGWO algorithm. J. Vis. Commun. Image Represent. 2021, 80, 103274. [Google Scholar] [CrossRef]
- Schork, N.; Schuhmann, S.; Nirschl, H.; Guthausen, G. Compressed sensing MRI to characterize sodium alginate deposits during cross-flow filtration in membranes with a helical ridge. J. Membr. Sci. 2021, 626, 119170. [Google Scholar] [CrossRef]
- Zhou, Y.H.; Tong, F.; Zhang, G.Q. Distributed compressed sensing estimation of underwater acoustic OFDM channel. Appl. Acoust. 2017, 117, 160–166. [Google Scholar] [CrossRef]
- Daponte, P.; De Vito, L.; Picariello, F.; Rapuano, S.; Tudosa, I. Compressed Sensing Technologies and Challenges for Aerospace and Defense RF Source Localization. In Proceedings of the 2018 5th IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace), Rome, Italy, 20–22 June 2018; pp. 634–639. [Google Scholar] [CrossRef]
- Kulkarni, K.; Lohit, S.; Turaga, P.; Kerviche, R.; Ashok, A. ReconNet: Non-Iterative Reconstruction of Images From Compressively Sensed Measurements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Chen, Q.; Chen, D.; Gong, J. Low-Complexity Adaptive Sampling of Block Compressed Sensing Based on Distortion Minimization. Sensors 2022, 22, 4806. [Google Scholar] [CrossRef]
- Yao, H.; Dai, F.; Zhang, S.; Zhang, Y.; Tian, Q.; Xu, C. Dr2-net: Deep residual reconstruction network for image compressive sensing. Neurocomputing 2019, 359, 483–493. [Google Scholar] [CrossRef]
- Shi, W.; Jiang, F.; Liu, S.; Zhao, D. Image Compressed Sensing Using Convolutional Neural Network. IEEE Trans. Image Process. 2020, 29, 375–388. [Google Scholar] [CrossRef]
- Sun, Y.; Yang, Y.; Liu, Q.; Chen, J.; Yuan, X.T.; Guo, G. Learning non-locally regularized compressed sensing network with half-quadratic splitting. IEEE Trans. Multimed. 2020, 22, 3236–3248. [Google Scholar] [CrossRef]
- Sun, Y.; Chen, J.; Liu, Q.; Liu, B.; Guo, G. Dual-path attention network for compressed sensing image reconstruction. IEEE Trans. Image Process. 2020, 29, 9482–9495. [Google Scholar] [CrossRef]
- Metzler, C.; Mousavi, A.; Baraniuk, R. Learned D-AMP: Principled neural network based compressive image recovery. Adv. Neural Inf. Process. Syst. 2017, 30, 1770–1781. [Google Scholar]
- Zhang, J.; Ghanem, B. ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 1828–1837. [Google Scholar]
- You, D.; Xie, J.; Zhang, J. ISTA-NET++: Flexible Deep Unfolding Network for Compressive Sensing. In Proceedings of the 2021 IEEE International Conference on Multimedia and Expo (ICME), Shenzhen, China, 5–9 July 2021; pp. 1–6. [Google Scholar] [CrossRef]
- Zhang, J.; Zhao, C.; Gao, W. Optimization-inspired compact deep compressive sensing. IEEE J. Sel. Top. Signal Process. 2020, 14, 765–774. [Google Scholar] [CrossRef]
- Xia, K.; Pan, Z.; Mao, P. Video Compressive Sensing Reconstruction Using Unfolded LSTM. Sensors 2022, 22, 7172. [Google Scholar] [CrossRef] [PubMed]
- Shi, W.; Caballero, J.; Huszár, F.; Totz, J.; Aitken, A.P.; Bishop, R.; Rueckert, D.; Wang, Z. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. arXiv 2016, arXiv:1609.05158. [Google Scholar]
- Li, N.; Zhou, C.C. AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing. In Proceedings of the 2020 IEEE 20th International Conference on Communication Technology (ICCT), Nanning, China, 28–31 October 2020; pp. 1338–1344. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 6000–6010. [Google Scholar]
- Lin, T.Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 6–12 September 2014; pp. 740–755. [Google Scholar]
- Bevilacqua, M.; Roumy, A.; Guillemot, C.; Alberi Morel, M.L. Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. In Proceedings of the British Machine Vision Conference 2012, Surrey, UK, 3–7 September 2012; pp. 135.1–135.10. [Google Scholar] [CrossRef]
- Zeyde, R.; Elad, M.; Protter, M. On single image scale-up using sparse-representations. In Proceedings of the International Conference on Curves and Surfaces, Avignon, France, 24–30 June 2010; pp. 711–730. [Google Scholar]
- Martin, D.; Fowlkes, C.; Tal, D.; Malik, J. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proceedings of the Eighth IEEE International Conference on Computer Vision. ICCV 2001, Vancouver, BC, Canada, 7–14 July 2001; Volume 2, pp. 416–423. [Google Scholar]
- Huang, J.B.; Singh, A.; Ahuja, N. Single image super-resolution from transformed self-exemplars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 5197–5206. [Google Scholar]
- Wang, Z.; Bovik, A.; Sheikh, H.; Simoncelli, E. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 2004, 13, 600–612. [Google Scholar] [CrossRef]
- Wang, M.; Wei, S.; Liang, J.; Zhou, Z.; Qu, Q.; Shi, J.; Zhang, X. TPSSI-Net: Fast and Enhanced Two-Path Iterative Network for 3D SAR Sparse Imaging. IEEE Trans. Image Process. 2021, 30, 7317–7332. [Google Scholar] [CrossRef]
- You, D.; Zhang, J.; Xie, J.; Chen, B.; Ma, S. Coast: Controllable arbitrary-sampling network for compressive sensing. IEEE Trans. Image Process. 2021, 30, 6066–6080. [Google Scholar] [CrossRef]
- Song, J.; Chen, B.; Zhang, J. Memory-Augmented Deep Unfolding Network for Compressive Sensing. In Proceedings of the 29th ACM International Conference on Multimedia, Virtual Event, 20–24 October 2021; Association for Computing Machinery: New York, NY, USA, 2021; pp. 4249–4258. [Google Scholar] [CrossRef]
Dataset | Number | Comments |
---|---|---|
Set5 | 5 | Red-Green-Blue (RGB), unfixed resolutions |
Set11 | 11 | Gray, unfixed resolutions |
Set14 | 14 | 2 Gray, 12 RGB, unfixed resolutions |
BSD68 | 68 | RGB, fixed resolution |
Urban100 | 100 | RGB, unfixed high-resolution city images |
Methods | R | Set5 | Set11 | Set14 | BSD68 | Urban100 | Avg ± Std |
---|---|---|---|---|---|---|---|
Reconnet [23] | 1% | 20.66/0.5211 | 19.34/0.4716 | 20.15/0.4650 | 21.16/0.4816 | 18.32/0.4261 | 19.92 ± 1.00/0.4731 ± 0.0305 |
4% | 24.45/0.6599 | 22.63/0.6115 | 23.16/0.5813 | 23.58/0.5760 | 20.82/0.5426 | 22.93 ± 1.21/0.5943 ± 0.0394 | |
10% | 27.82/0.7824 | 25.87/0.7459 | 25.90/0.6937 | 25.79/0.6763 | 23.38/0.6697 | 25.75 ± 1.41/0.7136 ± 0.0436 | |
25% | 31.93/0.8796 | 29.80/0.8578 | 29.28/0.8137 | 28.74/0.7965 | 26.84/0.8020 | 29.32 ± 1.64/0.8299 ± 0.0329 | |
50% | 35.80/0.9350 | 33.89/0.9260 | 32.96/0.9013 | 32.22/0.8932 | 30.69/0.8954 | 33.11 ± 1.70/0.9102 ± 0.0170 | |
Avg. | 28.13/0.7556 | 26.31/0.7225 | 26.29/0.6910 | 26.30/0.6847 | 24.01/0.6671 | 26.21 ± 1.31/0.7042 ± 0.0313 | |
ISTA-Net++ [31] | 1% | 22.21/0.5872 | 20.43/0.5235 | 21.24/0.5118 | 22.09/0.5095 | 19.27/0.4682 | 21.05 ± 1.10/0.5200 ± 0.0384 |
4% | 26.53/0.7968 | 24.85/0.7528 | 24.79/0.6858 | 24.80/0.6557 | 22.71/0.6768 | 24.74 ± 1.21/0.7136 ± 0.0528 | |
10% | 31.47/0.9111 | 29.82/0.8972 | 28.63/0.8220 | 27.64/0.7858 | 27.53/0.8513 | 29.02 ± 1.48/0.8535 ± 0.0465 | |
25% | 36.09/0.9577 | 34.78/0.9569 | 33.03/0.9146 | 31.23/0.8939 | 32.48/0.9393 | 33.52 ± 1.72/0.9325 ± 0.0248 | |
50% | 41.43/0.9824 | 40.19/0.9833 | 38.28/0.9672 | 36.08/0.9615 | 38.14/0.9794 | 38.82 ± 1.84/0.9747 ± 0.0088 | |
Avg. | 31.55/0.8470 | 30.02/0.8227 | 29.19/0.7803 | 28.37/0.7613 | 28.03/0.7830 | 29.43 ± 1.26/0.7989 ± 0.0313 | |
CSNET+ [26] | 1% | 24.57/0.6853 | 22.70/0.6257 | 23.20/0.6027 | 23.94/0.5876 | 21.03/0.5591 | 23.09 ± 1.21/0.6121 ± 0.0425 |
4% | 29.20/0.8799 | 26.78/0.8421 | 26.72/0.7816 | 26.58/0.7555 | 24.26/0.7658 | 26.71 ± 1.56/0.8050 ± 0.0480 | |
10% | 32.97/0.9418 | 30.38/0.9188 | 29.68/0.8740 | 28.93/0.8519 | 27.26/0.8687 | 29.84 ± 1.88/0.8910 ± 0.0337 | |
25% | 37.35/0.9721 | 35.00/0.9629 | 33.69/0.9407 | 32.55/0.9320 | 31.56/0.9423 | 34.03 ± 2.02/0.9500 ± 0.0150 | |
50% | 42.47/0.9879 | 40.77/0.9876 | 38.75/0.9768 | 37.56/0.9772 | 36.96/0.9798 | 39.30 ± 2.05/0.9819 ± 0.0049 | |
Avg. | 33.31/0.8934 | 31.13/0.8674 | 30.41/0.8352 | 29.91/0.8209 | 28.21/0.8232 | 30.59 ± 1.66/0.8480 ± 0.0281 | |
AMPNet [4] | 1% | 24.74/0.6989 | 21.61/0.6201 | 23.41/0.6153 | 24.10/0.5967 | 21.34/0.5803 | 23.04 ± 1.35/0.6222 ± 0.0408 |
4% | 29.44/0.8878 | 26.13/0.8433 | 27.14/0.7884 | 26.82/0.7593 | 24.89/0.7842 | 26.88 ± 1.49/0.8126 ± 0.0465 | |
10% | 33.84/0.9480 | 30.01/0.9202 | 30.43/0.8801 | 29.37/0.8551 | 28.67/0.8892 | 30.46 ± 1.79/0.8985 ± 0.0324 | |
25% | 38.31/0.9750 | 35.12/0.9676 | 34.93/0.9470 | 33.20/0.9337 | 33.88/0.9566 | 35.09 ± 1.75/0.9560 ± 0.0147 | |
50% | 43.53/0.9892 | 40.56/0.9868 | 40.08/0.9787 | 38.26/0.9774 | 39.34/0.9848 | 40.35 ± 1.77/0.9834 ± 0.0046 | |
Avg. | 33.97/0.8998 | 30.68/0.8676 | 31.20/0.8419 | 30.35/0.8244 | 29.63/0.8390 | 31.17 ± 1.49/0.8545 ± 0.0266 | |
COAST [44] | 1% | 24.05/0.6637 | 20.87/0.5836 | 22.70/0.5847 | 23.62/0.5749 | 20.74/0.5473 | 22.40 ± 1.37/0.5908 ± 0.0388 |
4% | 29.16/0.8813 | 25.55/0.8333 | 26.71/0.7816 | 26.56/0.7537 | 24.45/0.7738 | 26.49 ± 1.56/0.8048 ± 0.0464 | |
10% | 33.36/0.9445 | 29.45/0.9159 | 29.99/0.8761 | 29.11/0.8517 | 28.06/0.8811 | 29.99 ± 1.80/0.8938 ± 0.0326 | |
25% | 38.20/0.9742 | 35.03/0.9680 | 34.72/0.9465 | 33.08/0.9338 | 33.65/0.9565 | 34.94 ± 1.78/0.9558 ± 0.0145 | |
50% | 42.81/0.9879 | 39.58/0.9857 | 39.13/0.9770 | 37.66/0.9760 | 37.96/0.9820 | 39.43 ± 1.83/0.9817 ± 0.0047 | |
Avg. | 33.52/0.8903 | 30.10/0.8573 | 30.65/0.8332 | 30.00/0.8180 | 28.97/0.8281 | 30.65 ± 1.53/0.8454 ± 0.0259 | |
MADUN [45] | 1% | 24.91/0.7161 | 21.80/0.6412 | 23.46/0.6269 | 24.17/0.6042 | 21.56/0.6044 | 23.18 ± 1.31/0.6386 ± 0.0412 |
4% | 29.94/0.8984 | 26.56/0.8595 | 27.41/0.7985 | 27.03/0.7682 | 25.56/0.8094 | 27.30 ± 1.46/0.8268 ± 0.0463 | |
10% | 34.19/0.9503 | 30.42/0.9261 | 30.66/0.8856 | 29.59/0.8612 | 29.54/0.9052 | 30.88 ± 1.71/0.9057 ± 0.0310 | |
25% | 38.82/0.9757 | 35.88/0.9714 | 35.42/0.9509 | 33.52/0.9378 | 34.85/0.9634 | 35.70 ± 1.75/0.9599 ± 0.0139 | |
50% | 42.36/0.9862 | 39.31/0.9849 | 38.93/0.9746 | 36.99/0.9717 | 38.63/0.9839 | 39.25 ± 1.75/0.9802 ± 0.0059 | |
Avg. | 34.04/0.9053 | 30.79/0.8766 | 31.18/0.8473 | 30.26/0.8286 | 30.03/0.8533 | 31.26 ± 1.45/0.8622 ± 0.0264 | |
CSformer [3] | 1% | 25.22/0.7197 | 21.95/0.6241 | 23.88/0.6146 | 23.07/0.5591 | 21.94/0.5885 | 23.21 ± 1.24/0.6212 ± 0.0542 |
4% | 30.31/0.8686 | 26.93/0.8251 | 27.78/0.7581 | 25.91/0.7045 | 26.13/0.7803 | 27.41 ± 1.59/0.7873 ± 0.0562 | |
10% | 34.20/0.9262 | 30.66/0.9027 | 30.85/0.8515 | 28.28/0.8078 | 29.61/0.8762 | 30.72 ± 1.97/0.8729 ± 0.0411 | |
25% | 38.30/0.9619 | 35.46/0.9570 | 35.04/0.9316 | 31.91/0.9102 | 34.16/0.9470 | 34.97 ± 2.07/0.9415 ± 0.0188 | |
50% | 43.55/0.9845 | 41.04/0.9831 | 40.41/0.9730 | 37.16/0.9714 | 39.46/0.9811 | 40.32 ± 2.08/0.9786 ± 0.0054 | |
Avg. | 34.32/0.8922 | 31.21/0.8584 | 31.59/0.8258 | 29.27/0.7906 | 30.26/0.8346 | 31.33 ± 1.70/0.8403 ± 0.0339 | |
IEF-CSNET | 1% | 25.26/0.7285 | 22.21/0.6533 | 23.88/0.6363 | 24.33/0.6090 | 22.04/0.6275 | 23.54 ± 1.24/0.6509 ± 0.0414 |
4% | 30.31/0.9016 | 26.98/0.8656 | 27.82/0.8033 | 27.17/0.7706 | 26.27/0.8247 | 27.71 ± 1.39/0.8332 ± 0.0461 | |
10% | 34.64/0.9522 | 31.03/0.9324 | 31.09/0.8884 | 29.78/0.8626 | 30.29/0.9133 | 31.37 ± 1.71/0.9098 ± 0.0316 | |
25% | 39.00/0.9758 | 36.20/0.9721 | 35.71/0.9519 | 33.65/0.9381 | 35.36/0.9656 | 35.99 ± 1.73/0.9607 ± 0.0139 | |
50% | 44.17/0.9893 | 41.18/0.9877 | 40.65/0.9799 | 38.67/0.9791 | 40.29/0.9870 | 40.99 ± 1.80/0.9846 ± 0.0042 | |
Avg. | 34.68/0.9095 | 31.52/0.8822 | 31.83/0.8519 | 30.72/0.8319 | 30.85/0.8636 | 31.92 ± 1.44/0.8678 ± 0.0265 |
Methods | Ratio = 0.01 | Ratio = 0.01 |
---|---|---|
Reconnet | 137.17 | 132.62 |
ISTA-Net++ | 44.80 | 44.84 |
CSNET+ | 93.02 | 91.32 |
AMPNet | 39.95 | 37.52 |
COAST | 24.76 | 24.87 |
MADUN | 16.00 | 16.02 |
CSformer | - | 0.20 |
IEF-CSNET | 36.11 | 35.71 |
R = 0.01 | R = 0.5 | |||
---|---|---|---|---|
PSNR | SSIM | PSNR | SSIM | |
IIFE | 23.40 | 0.6291 | 40.28 | 0.9833 |
ECCE | 23.77 | 0.6519 | 41.18 | 0.9848 |
CIE | 23.70 | 0.6479 | 41.24 | 0.9849 |
ALL | 23.83 | 0.6551 | 41.31 | 0.9850 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhou, Z.; Liu, F.; Shen, H. IEF-CSNET: Information Enhancement and Fusion Network for Compressed Sensing Reconstruction. Sensors 2023, 23, 1886. https://doi.org/10.3390/s23041886
Zhou Z, Liu F, Shen H. IEF-CSNET: Information Enhancement and Fusion Network for Compressed Sensing Reconstruction. Sensors. 2023; 23(4):1886. https://doi.org/10.3390/s23041886
Chicago/Turabian StyleZhou, Ziqun, Fengyin Liu, and Haibin Shen. 2023. "IEF-CSNET: Information Enhancement and Fusion Network for Compressed Sensing Reconstruction" Sensors 23, no. 4: 1886. https://doi.org/10.3390/s23041886