Frequency-Aware Dual-Stream Learning for Balanced Realism and Fidelity in Electron Microscopy Imaging

• URL: http://arxiv.org/abs/2607.22765v1
• Date: Fri, 24 Jul 2026 03:09:05 GMT
• Title: Frequency-Aware Dual-Stream Learning for Balanced Realism and Fidelity in Electron Microscopy Imaging
• Abstract summary: Existing learning-based methods rely on single-stream architectures that struggle to balance perceptual realism and quantitative fidelity.<n>This work introduces a frequency-adaptive dual-stream architecture to resolve this conflict.<n> Experiments on the EMDiffuse dataset show the method achieves superior LPIPS and resolution ratio.
• Score: 13.214177321682373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Electron microscopy enables nanoscale cellular visualization but faces a trade-off between imaging resolution and acquisition speed. Existing learning-based methods rely on single-stream architectures that struggle to balance perceptual realism and quantitative fidelity, either over-smoothing details or generating unrealistic hallucinations. This work introduces a frequency-adaptive dual-stream architecture to resolve this conflict. Using discrete wavelet transform, we decompose images into low-frequency structures and high-frequency details, then employ a conditional diffusion model for realistic global synthesis and a transformer network for precise detail recovery. Experiments on the EMDiffuse dataset show the method achieves superior LPIPS and resolution ratio, substantially outperforming existing approaches. The method also shows strong generalization across diverse biological samples, supporting fast and reliable electron microscopy imaging for structural biology and nanotechnology applications. The source code and associated dataset are publicly available to facilitate further research.

Related papers

• Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy [0.0]
  Cross-modality image translation offers a route to super-resolution fluorescence microscopy from low-resolution images.<n>We propose a physics-informed generative adversarial network for confocal-to-STED image translation.
  arXiv  Detail & Related papers  (2026-07-23T11:16:26Z)
• FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion [22.180711075004538]
  FMRFusion is a frequency-aware representation learning network for Heterogeneous Image Fusion.<n>A Multi-Scale Struc tural Perception Module is introduced to capture discriminative structures.<n>A Cross-View Complementary Interaction is incorpo rated to explicitly model and fuse the complementary characteristics between reflected light information and radiative intensity responses.
  arXiv  Detail & Related papers  (2026-06-06T05:23:06Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Diffusion-Based Synthetic Brightfield Microscopy Images for Enhanced Single Cell Detection [0.0]
  We investigate the use of unconditional models to generate synthetic brightfield microscopy images.<n>A U-Net based diffusion model was trained and used to create datasets with varying ratios of synthetic and real images.<n>Experiments with YOLOv8, YOLOv9 and RT-DETR reveal that training with synthetic data can achieve improved detection accuracies.
  arXiv  Detail & Related papers  (2025-11-25T08:57:23Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• A novel attention mechanism for noise-adaptive and robust segmentation of microtubules in microscopy images [0.27185251060695437]
  We propose a novel noise-adaptive attention mechanism, extending the Squeeze-and-Excitation (SE) module, to dynamically adjust to varying noise levels.<n>This Adaptive SE (ASE) is integrated into a U-Net decoder, with residual encoder blocks, forming a lightweight yet powerful model: ab_Res_U-Net.<n>It effectively segmented microtubules in both synthetic and real noisy images, outperforming state-of-the-art curvilinear-structure segmentation methods.
  arXiv  Detail & Related papers  (2025-07-10T14:26:50Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  We propose a unified MRI reconstruction model robust to various measurement undersampling patterns and image resolutions.<n>Our model improves SSIM by 11% and PSNR by 4 dB over a state-of-the-art CNN (End-to-End VarNet) with 600$times$ faster inference than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Fluctuation-based deconvolution in fluorescence microscopy using plug-and-play denoisers [2.236663830879273]
  spatial resolution of images of living samples obtained by fluorescence microscopes is physically limited due to the diffraction of visible light. Several deconvolution and super-resolution techniques have been proposed to overcome this limitation.
  arXiv  Detail & Related papers  (2023-03-20T15:43:52Z)
• Deep learning at the edge enables real-time streaming ptychographic imaging [7.4083593332068975]
  Coherent microscopy techniques like ptychography are poised to revolutionize nanoscale materials characterization. Traditional approaches no longer suffice for recovering sample images in real-time from high-speed coherent imaging experiments. Here, we demonstrate a workflow that leverages artificial intelligence at the edge and high-performance computing to enable real-time inversion on X-ray ptychography data streamed directly from a detector at up to 2 kHz.
  arXiv  Detail & Related papers  (2022-09-20T02:02:37Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• A parameter refinement method for Ptychography based on Deep Learning concepts [55.41644538483948]
  coarse parametrisation in propagation distance, position errors and partial coherence frequently menaces the experiment viability. A modern Deep Learning framework is used to correct autonomously the setup incoherences, thus improving the quality of a ptychography reconstruction. We tested our system on both synthetic datasets and also on real data acquired at the TwinMic beamline of the Elettra synchrotron facility.
  arXiv  Detail & Related papers  (2021-05-18T10:15:17Z)
• Data-Driven Discovery of Molecular Photoswitches with Multioutput Gaussian Processes [51.17758371472664]
  Photoswitchable molecules display two or more isomeric forms that may be accessed using light. We present a data-driven discovery pipeline for molecular photoswitches underpinned by dataset curation and multitask learning. We validate our proposed approach experimentally by screening a library of commercially available photoswitchable molecules.
  arXiv  Detail & Related papers  (2020-06-28T20:59:03Z)

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.