XPAR-Net: cross-paradigm alignment and reconstruction network for high-fidelity lens-free on-chip microscopy
Abstract
Lens-free on-chip microscopy (LFOM) enables compact, wide-field imaging, yet reconstructing a complex field from a single in-line hologram involves two coupled challenges: phase must be inferred from an intensity-only measurement, while fringe-scale information must be recovered within a finite numerical-aperture bandwidth. We introduce XPAR-Net, which addresses these challenges through coordinated learning across complementary representation paradigms. Field-wide channel-relation modeling captures selective dependencies among holographic responses, whereas localized spatial refinement preserves fine structural variations. Cross-Domain Alignment and Fusion reconciles these representations and confines learnable spectral residual correction to the modeled acquisition support. Training further couples reference-domain complex-field fidelity with in-support spectral-profile, local-structural, and input-relative refinement constraints. On the complete 11-category in-distribution test set, XPAR-Net improved average PSNR by 1.28 dB and SSIM by 2.9% over HoloFormer, with only 8.8% of HoloFormer’s trainable parameters and 19.0% of its MACs for a 256× 256 input patch. These results highlight coordinated cross-paradigm modeling as an effective route to accurate and computationally compact single-frame LFOM reconstruction under the evaluated conditions.
Related
- High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics
- High-resolution holographic reconstruction combined with fluorescence microscopy to identify unwanted
- Learning Transferable Self-Supervised Priors for Super-Resolution Reconstruction in Structured Illumination Microscopy
- DAFNet: Dual-path Adaptive Fusion Network for High-Fidelity Cross-Modality Brain MR Image Synthesis
- IV-PAFNet: Infrared-visible cross-modal alignment and fusion network for nighttime UAV object detection
BibTeX
@article{zhao2026xparnet,
title = {{XPAR-Net: cross-paradigm alignment and reconstruction network for high-fidelity lens-free on-chip microscopy}},
author = {Yanbo Zhao and Xiongfei Su and Ning Xu and Yachen Gao},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-73646-w},
url = {https://www.nature.com/articles/s41598-026-73646-w},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - XPAR-Net: cross-paradigm alignment and reconstruction network for high-fidelity lens-free on-chip microscopy
AU - Yanbo Zhao
AU - Xiongfei Su
AU - Ning Xu
AU - Yachen Gao
PY - 2026
DA - 2026/10/21
JO - Scientific Reports
DO - 10.1038/s41598-026-73646-w
UR - https://www.nature.com/articles/s41598-026-73646-w
AB - Lens-free on-chip microscopy (LFOM) enables compact, wide-field imaging, yet reconstructing a complex field from a single in-line hologram involves two coupled challenges: phase must be inferred from an intensity-only measurement, while fringe-scale information must be recovered within a finite numerical-aperture bandwidth. We introduce XPAR-Net, which addresses these challenges through coordinated learning across complementary representation paradigms. Field-wide channel-relation modeling captures selective dependencies among holographic responses, whereas localized spatial refinement preserves fine structural variations. Cross-Domain Alignment and Fusion reconciles these representations and confines learnable spectral residual correction to the modeled acquisition support. Training further couples reference-domain complex-field fidelity with in-support spectral-profile, local-structural, and input-relative refinement constraints. On the complete 11-category in-distribution test set, XPAR-Net improved average PSNR by 1.28 dB and SSIM by 2.9% over HoloFormer, with only 8.8% of HoloFormer’s trainable parameters and 19.0% of its MACs for a 256× 256 input patch. These results highlight coordinated cross-paradigm modeling as an effective route to accurate and computationally compact single-frame LFOM reconstruction under the evaluated conditions.
SN - 2045-2322
ER -