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

2026-03-11

AI Summary

This work addresses the limitations of conventional thermal imaging methods, which neglect lateral heat diffusion, and the challenges faced by existing physics-informed neural networks in accurately reconstructing three-dimensional material properties in transient heat conduction inverse problems due to gradient stiffness. To overcome these issues, the authors propose NeFTY, a framework that models the 3D thermal diffusivity field as a continuous neural representation and optimizes it using a differentiable physics solver, embedding thermodynamic laws as hard constraints directly into the loss function. This approach effectively mitigates spectral bias and ill-posedness inherent in the inverse problem, enabling high-resolution, non-destructive reconstruction of subsurface defects at arbitrary scales. Evaluated on synthetic data, NeFTY significantly outperforms current baselines, achieving markedly improved accuracy in both 3D defect localization and thermophysical property reconstruction.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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/

Problem

• thermal tomography
• inverse heat conduction
• subsurface defect detection
• 3D material property reconstruction
• transient thermography

Innovation

• Neural Field Thermal Tomography
• differentiable physics
• inverse heat conduction
• 3D thermal tomography
• hard-constrained optimization