Deep Learning Empowered Sub-Diffraction Terahertz Backpropagation Single-Pixel Imaging

• URL: http://arxiv.org/abs/2505.07839v2
• Date: Sun, 03 Aug 2025 08:58:27 GMT
• Title: Deep Learning Empowered Sub-Diffraction Terahertz Backpropagation Single-Pixel Imaging
• Authors: Yongsheng Zhu, Shaojing Liu, Ximiao Wang, Runli Li, Haili Yang, Jiali Wang, Hongjia Zhu, Yanlin Ke, Ningsheng Xu, Huanjun Chen, Shaozhi Deng,
• Abstract summary: Terahertz single-pixel imaging (THz SPI) has garnered widespread attention for its potential to overcome challenges associated with THz focal plane arrays.<n>Here, we propose a sub-diffraction THz backpropagation SPI technique.<n>We illuminate the object with continuous-wave 0.36-THz radiation (lambda0 = 833.3 mum)<n>The transmitted THz wave is modulated by prearranged patterns generated on a 500-mum-thick silicon wafer and subsequently recorded by a far-field single-pixel detector.<n>An untrained neural network constrained with the physical SPI
• Score: 1.196682203233596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Terahertz single-pixel imaging (THz SPI) has garnered widespread attention for its potential to overcome challenges associated with THz focal plane arrays. However, the inherently long wavelength of THz waves limits imaging resolution, while achieving subwavelength resolution requires harsh experimental conditions and time-consuming processes. Here, we propose a sub-diffraction THz backpropagation SPI technique. We illuminate the object with continuous-wave 0.36-THz radiation ({\lambda}0 = 833.3 {\mu}m). The transmitted THz wave is modulated by prearranged patterns generated on a 500-{\mu}m-thick silicon wafer and subsequently recorded by a far-field single-pixel detector. An untrained neural network constrained with the physical SPI process iteratively reconstructs the THz images with an ultralow sampling ratio of 1.5625%, significantly reducing the long sampling times. To further suppress the THz diffraction-field effects, a backpropagation SPI from near field to far field is implemented by integrating with a THz physical propagation model into the output layer of the network. Notably, using the thick wafer where THz evanescent field cannot be fully recorded, we achieve a spatial resolution of 118 {\mu}m (~{\lambda}0/7) through backpropagation SPI, thus eliminating the need for ultrathin photomodulators. This approach provides an efficient solution for advancing THz microscopic imaging and addressing other inverse imaging challenges.

Related papers

• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing [92.61216319417208]
  We propose a novel frequency domain-based diffusion model, named ours, for fully exploiting the beneficial knowledge in unpaired clear data.<n>Inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction.
  arXiv  Detail & Related papers  (2025-07-02T01:22:46Z)
• On-demand acoustic shaping of Mossbauer gamma-ray photons [0.0]
  We transform the intensity of a quasi-monochromatic single-photon wave packet emitted by a radioactive M"ossbauer gamma-ray source into a sequence of short bursts with an arbitrary number of bursts, including a single burst. The technique allows one to individually and independently control, on demand, the moments of the burst appearance, as well as the peak intensity, duration and shape of each burst in the sequence. We show that the proposed technique can be implemented on the basis of currently available equipment with use of 14.4-keV recoilless photons, emitted by Co-57 source, and Fe-57 absorber.
  arXiv  Detail & Related papers  (2024-10-21T16:21:55Z)
• WAVE-UNET: Wavelength based Image Reconstruction method using attention UNET for OCT images [1.0835264351334324]
  We propose a systematic design methodology WAVE-UNET to reconstruct the high-quality OCT images directly from the lambda-space to reduce the complexity. This framework uses modified UNET having attention gating and residual connections, with IDFT processed lambda-space fringes as the input. The method consistently outperforms the traditional OCT system by generating good-quality B-scans with highly reduced time-complexity.
  arXiv  Detail & Related papers  (2024-10-05T11:16:10Z)
• Super-resolution imaging using super-oscillatory diffractive neural networks [31.825503659600702]
  Super-oscillatory diffractive neural network, i.e., SODNN, can achieve super-resolved spatial resolution for imaging beyond diffraction limit. SODNN is constructed by utilizing diffractive layers to implement optical interconnections and imaging samples or biological sensors. Our research work will inspire the development of intelligent optical instruments to facilitate the applications of imaging, sensing, perception, etc.
  arXiv  Detail & Related papers  (2024-06-27T12:16:35Z)
• Super-resolution of THz time-domain images based on low-rank representation [1.256245863497516]
  Tera time-domain spectroscopy (THz- TDS) employs sub-secondpicohertz pulses to probe materials. The spatial resolution of THz images is primarily limited by two sources: a non-zero THz beam waist and the acquisition step size. This work presents a super-resolution approach to restore THz time-domain images acquired with medium-to-big step sizes.
  arXiv  Detail & Related papers  (2023-12-21T13:11:57Z)
• WaveDM: Wavelet-Based Diffusion Models for Image Restoration [43.254438752311714]
  Wavelet-Based Diffusion Model (WaveDM) learns the distribution of clean images in the wavelet domain conditioned on the wavelet spectrum of degraded images after wavelet transform. WaveDM achieves state-of-the-art performance with the efficiency that is comparable to traditional one-pass methods.
  arXiv  Detail & Related papers  (2023-05-23T08:41:04Z)
• Hyper-entanglement between pulse modes and frequency bins [101.18253437732933]
  Hyper-entanglement between two or more photonic degrees of freedom (DOF) can enhance and enable new quantum protocols. We demonstrate the generation of photon pairs hyper-entangled between pulse modes and frequency bins.
  arXiv  Detail & Related papers  (2023-04-24T15:43:08Z)
• Large-scale single-photon imaging [10.210597636941937]
  Single-photon avalanche diode (SPAD) array has been widely applied in various fields such as fluorescence lifetime imaging and quantum computing. However, large-scale high-fidelity single-photon imaging remains a big challenge, due to the complex hardware manufacture craft and heavy noise disturbance of SPAD arrays. We introduce deep learning into SPAD, enabling super-resolution single-photon imaging over an order of magnitude, with significant enhancement of bit depth and imaging quality.
  arXiv  Detail & Related papers  (2022-12-28T00:38:04Z)
• Diffusion Probabilistic Model Made Slim [128.2227518929644]
  We introduce a customized design for slim diffusion probabilistic models (DPM) for light-weight image synthesis. We achieve 8-18x computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks.
  arXiv  Detail & Related papers  (2022-11-27T16:27:28Z)
• On-chip quantum information processing with distinguishable photons [55.41644538483948]
  Multi-photon interference is at the heart of photonic quantum technologies. Here, we experimentally demonstrate that detection can be implemented with a temporal resolution sufficient to interfere photons detuned on the scales necessary for cavity-based integrated photon sources. We show how time-resolved detection of non-ideal photons can be used to improve the fidelity of an entangling operation and to mitigate the reduction of computational complexity in boson sampling experiments.
  arXiv  Detail & Related papers  (2022-10-14T18:16:49Z)
• Quantum-limited millimeter wave to optical transduction [50.663540427505616]
  Long distance transmission of quantum information is a central ingredient of distributed quantum information processors. Current approaches to transduction employ solid state links between electrical and optical domains. We demonstrate quantum-limited transduction of millimeter-wave (mmwave) photons into optical photons using cold $85$Rb atoms as the transducer.
  arXiv  Detail & Related papers  (2022-07-20T18:04:26Z)
• Submegahertz spectral width photon pair source based on fused silica microspheres [0.0]
  High efficiency, sub-MHz bandwidth photon pair generators will enable the field of quantum technology to transition from laboratory demonstrations to transformational applications involving information transfer from photons to atoms. We use an ultra-high quality factor (Q) fused silica microsphere resonant cavity to form a photon pair generator. We demonstrate the extraction of the spectral profile of a single peak in the single-photon frequency comb from a measurement of the signal-idler time of emission distribution.
  arXiv  Detail & Related papers  (2021-10-25T23:56:19Z)
• Super-resolved imaging of a single cold atom on a nanosecond timescale [38.305954220018315]
  We demonstrate nano-scale two-second stroboscopic pictures of a single trapped ion beyond the optical diffraction limit. Our method provides a powerful tool for probing particle positions, momenta, and correlations, as well as their dynamics in cold atomic systems.
  arXiv  Detail & Related papers  (2021-04-20T15:07:54Z)
• Deep Unfolded Recovery of Sub-Nyquist Sampled Ultrasound Image [94.42139459221784]
  We propose a reconstruction method from sub-Nyquist samples in the time and spatial domain, that is based on unfolding the ISTA algorithm. Our method allows reducing the number of array elements, sampling rate, and computational time while ensuring high quality imaging performance.
  arXiv  Detail & Related papers  (2021-03-01T19:19:38Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)
• Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery [79.69449412334188]
  In this paper, we investigate how to adapt state-of-the-art residual learning based single gray/RGB image super-resolution approaches. We introduce a spatial-spectral prior network (SSPN) to fully exploit the spatial information and the correlation between the spectra of the hyperspectral data. Experimental results on some hyperspectral images demonstrate that the proposed SSPSR method enhances the details of the recovered high-resolution hyperspectral images.
  arXiv  Detail & Related papers  (2020-05-18T14:25:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.