17 October 2025 in IEEE Transactions on Computational Imaging
Single-shot digital holography has demonstrated great potential for capturing the complex amplitude of optical fields in lensless imaging systems. Nevertheless, accurately reconstructing intricate interference patterns remains challenging due to high-frequency texture distortion and limited generalization across diverse real-world conditions. To address these issues, we propose a physics-embedded network that explicitly incorporates angular spectrum propagation and spatial-domain amplitude constraints into a deep learning framework, ensuring both physical consistency and strong representational capacity. Building on this foundation, we devised HoloSSL, a physics-aware heterogeneous self-supervised learning framework for robust single-frame holographic reconstruction. The framework consists of two complementary stages: (1) physics-aware self-supervised pretraining using Hermite-Gaussian synthesized holograms to learn a prior-consistent mapping, and (2) unsupervised domain adaptation using real captured intensity-only holograms, where intensity fidelity and propagation consistency jointly guide label-free fine-tuning. To enhance texture representation, we design a swin-hourglass block that integrates cross-scale self-attention with frequency-aware modeling. Extensive simulations and real-world experiments demonstrate that HoloSSL outperforms state-of-the-art methods in terms of reconstruction fidelity, structural consistency, and robustness to noise, providing a new paradigm for adaptive, interpretable, and high-fidelity holographic imaging.
26 March 2026 in IEEE Transactions on Instrumentation and Measurement
Single-frame lens-free on-chip microscopy (LFOM) offers a compact and cost-effective solution for biomedical diagnostics and micro/nanoscale inspection but suffers from severe twin-image artifacts and frequency-dependent degradation due to numerical aperture (NA) limitations. Existing reconstruction methods often neglect the heterogeneous frequency sensitivity of LFOM and fail to explicitly suppress artifacts, leading to suboptimal complex-field measurement quality. To address these challenges, we propose SEMNet, a spectral-expert measurement network that introduces frequency-aware modeling into single-frame LFOM reconstruction. Specifically, SEMNet transforms captured holograms into polar Fourier space, partitions them into directional subbands, and adaptively routes each subband via a soft top-k gating mechanism to lightweight expert networks specialized for low-, mid-, and high-frequency restoration. A physics-consistent loss jointly enforces complex-field fidelity, Fresnel-likelihood consistency, twin-image suppression, and spectral load balancing, thereby aligning the reconstruction objective with physical imaging principles. Extensive experiments on 404 high-resolution hologram–complex field pairs from seven types of biological tissues demonstrate that SEMNet improves peak signal-to-noise ratio by up to 1.7 dB over strong single-frame baselines, with statistically significant gains in structural similarity indices (p < 0.001). SEMNet restores high-frequency textures while suppressing NA-boundary artifacts. It delivers 47.1 FPS end-to-end inference with 100× fewer parameters than a representative CNN baseline and 5× fewer MACs than a representative Transformer baseline, highlighting a frequency-structured, physics-aligned design for efficient LFOM.
18 May 2026 in IEEE Transactions on Computational Imaging
Single-shot digital holographic reconstruction is intrinsically ill-posed due to missing phase information, resulting in conjugate artifacts and degraded high-frequency fidelity, while existing convolutional and Transformer-based models inadequately capture long-range diffraction behavior and essential physical constraints. To address this challenge, we propose HoloMamba, a physics-aligned state-space framework for high-fidelity single-shot hologram reconstruction. The proposed model adopts a dual-branch hourglass architecture with bidirectional Mamba propagation, enabling efficient modeling of forward and backward spatial dependencies while preserving complex-domain consistency in linear time. To further incorporate physical priors, a spectral- and numerical-aperture-aware fusion strategy is introduced to adaptively balance global contextual modeling and directional state propagation across frequency bands. In addition, a curriculum-guided spectral regularization scheme is designed to progressively enforce band-wise consistency, thereby stabilizing high-frequency reconstruction during training. Extensive experiments on biological specimens and standard resolution targets demonstrate that HoloMamba consistently achieves superior amplitude and phase reconstruction accuracy compared with state-of-the-art convolutional and Transformer-based methods, while exhibiting enhanced robustness to axial misplacement and distribution shifts. These results validate the effectiveness of integrating structured state-space modeling with physics-informed spectral learning, and establish a principled approach for physics-aware holographic reconstruction in lensless microscopy and related computational imaging applications.
20 November 2025 in Biomedical Signal Processing and Control