Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Physics-driven generative adversarial networks empower single-pixel infrared hyperspectral imaging (2311.13626v1)

Published 22 Nov 2023 in eess.IV, cs.AI, cs.IR, and physics.optics

Abstract: A physics-driven generative adversarial network (GAN) was established here for single-pixel hyperspectral imaging (HSI) in the infrared spectrum, to eliminate the extensive data training work required by traditional data-driven model. Within the GAN framework, the physical process of single-pixel imaging (SPI) was integrated into the generator, and the actual and estimated one-dimensional (1D) bucket signals were employed as constraints in the objective function to update the network's parameters and optimize the generator with the assistance of the discriminator. In comparison to single-pixel infrared HSI methods based on compressed sensing and physics-driven convolution neural networks, our physics-driven GAN-based single-pixel infrared HSI can achieve higher imaging performance but with fewer measurements. We believe that this physics-driven GAN will promote practical applications of computational imaging, especially various SPI-based techniques.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Iqbal H Sarker. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2(6):420, 2021.
  2. Machine learning: trends, perspectives, and prospects. Science, 349(6245):255–260, 2015.
  3. Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19(6):1236–1246, 2018.
  4. Federated learning-based ai approaches in smart healthcare: concepts, taxonomies, challenges and open issues. Cluster Computing, 26(4):2271–2311, 2023.
  5. An introduction to deep learning in natural language processing: models, techniques, and tools. Neurocomputing, 470:443–456, 2022.
  6. Traffic flow prediction models–a review of deep learning techniques. Cogent Engineering, 9(1):2010510, 2022.
  7. Recent advances and applications of deep learning methods in materials science. npj Computational Materials, 8(1):59, 2022.
  8. Deep learning modeling in microscopy imaging: a review of materials science applications. Progress in Materials Science, page 101165, 2023.
  9. Deep-learning-based ghost imaging. Scientific Reports, 7(1):17865, 2017.
  10. Single-pixel imaging based on deep learning. arXiv preprint arXiv:2310.16869v1, 2023.
  11. Single-pixel imaging for edge images using deep neural networks. Applied Optics, 61(26):7793–7797, 2022.
  12. Low sampling high quality image reconstruction and segmentation based on array network ghost imaging. Optics Express, 31(6):9945–9960, 2023.
  13. Deep learning based projector defocus compensation in single-pixel imaging. Optics Express, 28(17):25134–25148, 2020.
  14. Improving imaging quality of real-time fourier single-pixel imaging via deep learning. Sensors, 19(19):4190, 2019.
  15. A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1):46, 2023.
  16. L. Brigato and L. Iocchi. A close look at deep learning with small data. arXiv preprint arXiv:2003.12843v1, 2020.
  17. Deep image prior. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9446–9454, 2018.
  18. Phase imaging with an untrained neural network. Light: Science & Applications, 9(1):77, 2020.
  19. A compressed reconstruction network combining deep image prior and autoencoding priors for single-pixel imaging. In Photonics, volume 9, page 343. MDPI, 2022.
  20. Mixture-net: low-rank deep image prior inspired by mixture models for spectral image recovery. Signal Processing, page 109296, 2023.
  21. Deep phase decoder: self-calibrating phase microscopy with an untrained deep neural network. Optica, 7(6):559–562, 2020.
  22. Spectral imaging: principles and applications. Cytometry Part A: The Journal of the International Society for Analytical Cytology, 69(8):735–747, 2006.
  23. Identification of minerals in hyperspectral imagery based on the attenuation spectral absorption index vector using a multilayer perceptron. Remote Sensing Letters, 12(5):449–458, 2021.
  24. Intraoperative guidance using hyperspectral imaging: a review for surgeons. Diagnostics, 11(11):2066, 2021.
  25. Hyperspectral imaging in environmental monitoring: a review of recent developments and technological advances in compact field deployable systems. Sensors, 19(14):3071, 2019.
  26. Single-pixel hyperspectral imaging via an untrained convolutional neural network. In Photonics, volume 10, page 224. MDPI, 2023.
  27. High-resolution hyperspectral single-pixel imaging system based on compressive sensing. Optical Engineering, 51(7):071406–071406, 2012.
  28. Fast full-color computational imaging with single-pixel detectors. Optics express, 21(20):23068–23074, 2013.
  29. Single-pixel infrared and visible microscope. Optica, 1(5):285–289, 2014.
  30. Compressive hyperspectral imaging by random separable projections in both the spatial and the spectral domains. Applied Optics, 52(10):D46–D54, 2013.
  31. Compressive sensing and adaptive direct sampling in hyperspectral imaging. Digital Signal Processing, 26:113–126, 2014.
  32. Compressive single-pixel hyperspectral imaging using rgb sensors. Optics Express, 29(7):11207–11220, 2021.
  33. Hadamard transform-based hyperspectral imaging using a single-pixel detector. Optics Express, 28(11):16126–16139, 2020.
  34. Broadband near-infrared hyperspectral single pixel imaging for chemical characterization. Optics Express, 27(9):12666–12672, 2019.
  35. Deep neural networks for single-pixel compressive video reconstruction. In Unconventional Optical Imaging II, volume 11351, pages 71–80. SPIE, 2020.
  36. Hazardous gas detection for ftir-based hyperspectral imaging system using dnn and cnn. In Electro-Optical and Infrared Systems: Technology and Applications XIV, volume 10433, pages 341–349. SPIE, 2017.
  37. Compressive hyperspectral image reconstruction with deep neural networks. In Big Data: Learning, Analytics, and Applications, volume 10989, pages 163–169. SPIE, 2019.
  38. Dnn-based hyperspectral image denoising with spatio-spectral pre-training. In 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), pages 568–572. IEEE, 2019.
  39. Hyperspectral image super-resolution using deep feature matrix factorization. IEEE Transactions on Geoscience and Remote Sensing, 57(8):6055–6067, 2019.
  40. A compressive sensing and unmixing scheme for hyperspectral data processing. IEEE Transactions on Image Processing, 21(3):1200–1210, 2011.
  41. Fast full-color computational imaging with single-pixel detectors. Optics Express, 21(20):23068–23074, 2013.
  42. Hadamard transform-based hyperspectral imaging using a single-pixel detector. Optics express, 28(11):16126–16139, 2020.
  43. Far-field super-resolution ghost imaging with a deep neural network constraint. Light: Science & Applications, 2022.
  44. Principles and prospects for single-pixel imaging. Nature Photonics, 13(1):13–20, 2019.
  45. Differential ghost imaging. Physical Review Letters, 104(25):253603, 2010.
  46. Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593v1, 2017.
  47. SPI-GAN: towards single-pixel imaging through generative adversarial network. arXiv preprint arXiv:2107.01330, 2021.
  48. Generative adversarial networks: an overview. IEEE Signal Processing Magazine, 35(1):53–65, 2018.
  49. Fast single-pixel imaging based on optimized reordering hadamard basis. Acta Phys. Sin., 68(6):064202, 2019.
  50. Chengbo Li. An efficient algorithm for total variation regularization with applications to the single pixel camera and compressive sensing. Rice University, 2010.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now