An Electric Potential-Augmented Benchmark Dataset for Physics-Guided Image Reconstruction of Electrical Capacitance Tomography

• URL: http://arxiv.org/abs/2606.12226v1
• Date: Wed, 10 Jun 2026 15:36:58 GMT
• Title: An Electric Potential-Augmented Benchmark Dataset for Physics-Guided Image Reconstruction of Electrical Capacitance Tomography
• Abstract summary: We propose an electric potential-augmented ECT benchmark dataset to explicitly integrate latent physics behind ECT.<n>The dataset comprises 20,000 randomized samples across four typical flow patterns.<n>We demonstrate how the inclusion of electric potential maps enhances modeling accuracy and robustness.
• Score: 2.8964660061423166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While deep learning has significantly advanced image reconstruction of Electrical Capacitance Tomography (ECT), most data-driven methods map directly between capacitance and permittivity distribution, treating the sensor as a black box. This overlooks the electric potential field -- the fundamental physical link governing the nonlinear and ill-posed ``soft-field'' effect. To address this, we propose an electric potential-augmented ECT benchmark dataset designed to explicitly integrate latent physics behind ECT into the learning process. Generated via a COMSOL-MATLAB pipeline for an eight-electrode sensor as an example, the dataset comprises 20,000 randomized samples across four typical flow patterns. Crucially, alongside the conventional capacitance vectors and permittivity distributions depicted as images, each sample preserves eight excitation-wise full-field potential maps. Beyond data release, we provide illustrative evaluation protocols for both forward and inverse problems of ECT. Through comprehensive testing on both in-distribution (IID) and out-of-distribution (OOD) scenarios, we systematically demonstrate how the inclusion of electric potential maps enhances modeling accuracy and robustness. Fundamentally, the explicit inclusion of latent field information significantly lowers the barrier to integrating physical laws into ECT modeling, thereby establishing a standardized foundation for future physics-guided machine learning of ECT image reconstruction.

Related papers

• Direct Dual-Energy CT Material Decomposition using Model-based Denoising Diffusion Model [105.95160543743984]
  We propose a deep learning procedure called Dual-Energy Decomposition Model-based Diffusion (DEcomp-MoD) for quantitative material decomposition.<n>We show that DEcomp-MoD outperform state-of-the-art unsupervised score-based model and supervised deep learning networks.
  arXiv  Detail & Related papers  (2025-07-24T01:00:06Z)
• Interaction Field Matching: Overcoming Limitations of Electrostatic Models [85.87349969357068]
  Electrostatic field matching (EFM) has recently appeared as a physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor.<n>We propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one.<n>We show the performance on a series of toy and image data transfer problems.
  arXiv  Detail & Related papers  (2025-06-03T14:45:14Z)
• Electrical Impedance Tomography for Anisotropic Media: a Machine Learning Approach to Classify Inclusions [0.18749305679160366]
  We consider the problem of identifying one or multiple inclusions in a background-conducting body $OmegasubsetmathbbR2$.<n>Our model, combined with the machine learning techniques of Artificial Neural Networks (ANN) and Support Vector Machines (SVM), may be used to determine the size of the inclusion, the presence of multiple inclusions, and also that of anisotropy within the inclusion(s)<n>We achieve a high rate of inclusion detection and show that two measurements are sufficient to achieve a good level of accuracy when predicting the size of an inclusion.
  arXiv  Detail & Related papers  (2025-02-06T18:15:54Z)
• Field Matching: an Electrostatic Paradigm to Generate and Transfer Data [85.96146230529264]
  We propose a novel method for generative modeling and distribution transfer tasks.<n>Our approach is inspired by the physics of an electrical capacitor.<n>In practice, we demonstrate the performance of our EFM in toy and image data experiments.
  arXiv  Detail & Related papers  (2025-02-04T14:50:16Z)
• A Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction [3.2814751789071273]
  Electrical impedance tomography (EIT) is a non-invasive imaging technique, capable of reconstructing images of the electrical conductivity of tissues and materials.<n>EIT image reconstruction is ill-posed due to the mismatch between the under-sampled voltage data and the high-resolution conductivity image.<n>A novel method based on the conditional diffusion model for EIT reconstruction is proposed, termed CDEIT.
  arXiv  Detail & Related papers  (2024-12-22T11:43:00Z)
• CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Information [61.1904164368732]
  We propose CognitionCapturer, a unified framework that fully leverages multimodal data to represent EEG signals.<n>Specifically, CognitionCapturer trains Modality Experts for each modality to extract cross-modal information from the EEG modality.<n>The framework does not require any fine-tuning of the generative models and can be extended to incorporate more modalities.
  arXiv  Detail & Related papers  (2024-12-13T16:27:54Z)
• Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling [10.926841288976684]
  We present a novel energy-based generative framework, Variational Potential Flow (VAPO) VAPO aims to learn a potential energy function whose gradient (flow) guides the prior samples, so that their density evolution closely follows an approximate data likelihood homotopy. Images can be generated after training the potential energy, by initializing the samples from Gaussian prior and solving the ODE governing the potential flow on a fixed time interval.
  arXiv  Detail & Related papers  (2024-07-21T18:08:12Z)
• End-to-End Model-based Deep Learning for Dual-Energy Computed Tomography Material Decomposition [53.14236375171593]
  We propose a deep learning procedure called End-to-End Material Decomposition (E2E-DEcomp) for quantitative material decomposition. We show the effectiveness of the proposed direct E2E-DEcomp method on the AAPM spectral CT dataset.
  arXiv  Detail & Related papers  (2024-06-01T16:20:59Z)
• Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential [2.6531366443213846]
  Dielectrics are crucial for technologies like flash memory, CPUs, photovoltaics, and capacitors. Existing machine learning models have focused on predicting scalar polycrystalline dielectric constants. We develop an equivariant readout decoder to predict total, electronic, and ionic dielectric tensors.
  arXiv  Detail & Related papers  (2024-05-15T02:58:19Z)
• Imaging ferroelectric domains with a single-spin scanning quantum sensor [0.0]
  Here, we use a scanning nitrogen-vacancy (NV) microscope to image domain patterns in piezoelectric and improper ferroelectric materials. The ability to measure both stray electric and magnetic fields under ambient conditions opens exciting opportunities for the study of multiferroic and multifunctional materials and devices.
  arXiv  Detail & Related papers  (2022-12-15T15:41:53Z)
• CGAN-ECT: Tomography Image Reconstruction from Electrical Capacitance Measurements Using CGANs [0.0]
  We propose a Conditional Generative Adversarial Network (CGAN) model for reconstructing ECT images from capacitance measurements. CGAN-ECT achieved an average image correlation coefficient of more than 99.3% and an average relative image error about 0.07.
  arXiv  Detail & Related papers  (2022-09-07T13:08:38Z)
• Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction [51.80191416661064]
  We propose a novel vision transformer with latent variables following an informative energy-based prior for salient object detection. Both the vision transformer network and the energy-based prior model are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation. With the generative vision transformer, we can easily obtain a pixel-wise uncertainty map from an image, which indicates the model confidence in predicting saliency from the image.
  arXiv  Detail & Related papers  (2021-12-27T06:04:33Z)

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.