Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation

• URL: http://arxiv.org/abs/2603.11045v1
• Date: Wed, 11 Mar 2026 17:59:42 GMT
• Title: Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
• Abstract summary: We propose a differentiable physics framework for the quantitative 3D reconstruction of material properties from transient surface temperature measurements.<n>NeFTY parameterizes the 3D diffusivity field as a continuous neural field optimized through a rigorous numerical solver.<n>Our approach enforces thermodynamic laws as hard constraints while maintaining the memory efficiency required for high-resolution 3D tomography.
• Score: 3.697746606429496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Neural Field Thermal Tomography (NeFTY), a differentiable physics framework for the quantitative 3D reconstruction of material properties from transient surface temperature measurements. While traditional thermography relies on pixel-wise 1D approximations that neglect lateral diffusion, and soft-constrained Physics-Informed Neural Networks (PINNs) often fail in transient diffusion scenarios due to gradient stiffness, NeFTY parameterizes the 3D diffusivity field as a continuous neural field optimized through a rigorous numerical solver. By leveraging a differentiable physics solver, our approach enforces thermodynamic laws as hard constraints while maintaining the memory efficiency required for high-resolution 3D tomography. Our discretize-then-optimize paradigm effectively mitigates the spectral bias and ill-posedness inherent in inverse heat conduction, enabling the recovery of subsurface defects at arbitrary scales. Experimental validation on synthetic data demonstrates that NeFTY significantly improves the accuracy of subsurface defect localization over baselines. Additional details at https://cab-lab-princeton.github.io/nefty/

Related papers

• Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion [1.4740287473718565]
  High-dimensional transient heat diffusion under noisy boundary conditions exposes a fundamental limitation of classical numerical methods.<n>This paper presents a Physics-Informed Neural Network (PINN) framework as a systematic solution to this problem.<n>PINN sustains approximately 91% accuracy while Finite Difference Method (FDM) collapses to 36%, a clear decisive advantage.
  arXiv  Detail & Related papers  (2026-06-06T05:13:47Z)
• Faster Thermal Profiling of a Lunar Rover with Machine Learning Adapted Finite Difference Model [3.3836709236378746]
  This paper presents a PIML framework for thermal analysis of a simplified lunar rover with internal heat sources.<n>A differentiable finite-difference thermal simulator is embedded within the framework to enforce physical consistency.<n>Results show that the PIML framework improves prediction accuracy by 50% and 39% relative to the coarse-mesh physics model.
  arXiv  Detail & Related papers  (2026-05-26T20:11:06Z)
• 3D Magnetic Field Reconstruction and Mapping with Physics-Informed Neural Networks [11.823793229327954]
  This study proposes an advanced Physics-Informed Neural Network framework for high-precision 3D magnetic field mapping.<n>The proposed PINN integrates Maxwell's equations directly into the loss function, enforcing divergence-free and curl-free conditions.<n> validation using simulated data achieves a reconstruction accuracy of $10-4$, a tenfold improvement over existing PINN benchmarks.
  arXiv  Detail & Related papers  (2026-05-25T09:42:27Z)
• GeoFunFlow-3D: A Physics-Guided Generative Flow Matching Framework for High-Fidelity 3D Aerodynamic Inference over Complex Geometries [5.068156424858535]
  GeoFunFlow-3D is a physics-guided generative flow matching framework.<n>We introduce a high-order discrete engine without automatic differentiation (No-AD) to reduce gradient stiffness.<n>For the NASA Rotor37 test, it accurately captures 3D detached shock structures.
  arXiv  Detail & Related papers  (2026-04-25T15:24:13Z)
• Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction [8.953088273349499]
  Physics-informed neural networks (PINNs) integrate physical principles into machine learning models.<n>PINNs embed physical principles only in loss functions, leading to slow convergence, optimization instability, and spectral bias.<n>This work introduces architecture physics embedded (PE)-PINN, which integrates additional physical guidance directly into the neural network architecture.
  arXiv  Detail & Related papers  (2026-02-13T04:28:23Z)
• Real-time distortion prediction in metallic additive manufacturing via a physics-informed neural operator approach [3.607834195988809]
  This paper proposes a physics-informed smart Neuralhorizon Operator (PINO) to predict z and y-direction for the future 15 s.<n>The performance of PINO model highlights its potential for real-time long-time distortion field prediction in controlling defects.
  arXiv  Detail & Related papers  (2025-11-17T09:37:04Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• Physics Informed Neural Networks for design optimisation of diamond particle detectors for charged particle fast-tracking at high luminosity hadron colliders [70.66815108184498]
  Future high-luminosity hadron colliders demand tracking detectors with extreme radiation tolerance, high spatial precision, and sub-nanosecond timing.<n>3D diamond pixel sensors offer these capabilities due to diamond's radiation hardness and high carrier mobility.<n>We model the phenomenon through a 3rd-order, 3+1D PDE derived as a quasi-stationary approximation of Maxwell's equations.
  arXiv  Detail & Related papers  (2025-09-25T13:09:28Z)
• Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields [66.1612475655465]
  3D reconstruction of deformable surfaces from RGB videos is a challenging problem.<n>Existing methods use deformation models with statistical, neural, or physical priors.<n>We propose ThinShell-SfT, a new method for non-rigid 3D tracking meshes.
  arXiv  Detail & Related papers  (2025-03-25T18:00:46Z)
• Physics-constrained coupled neural differential equations for one dimensional blood flow modeling [0.3749861135832073]
  Computational cardiovascular flow modeling plays a crucial role in understanding blood flow dynamics.<n>Traditional 1D models based on finite element methods (FEM) often lack accuracy compared to 3D averaged solutions.<n>This study introduces a novel physics-constrained machine learning technique that enhances the accuracy of 1D blood flow models.
  arXiv  Detail & Related papers  (2024-11-08T15:22:20Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model [63.685132323224124]
  Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains. In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges. Experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
  arXiv  Detail & Related papers  (2024-03-15T06:26:46Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• {\phi}-SfT: Shape-from-Template with a Physics-Based Deformation Model [69.27632025495512]
  Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera. This paper proposes a new SfT approach explaining 2D observations through physical simulations.
  arXiv  Detail & Related papers  (2022-03-22T17:59:57Z)

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.