Search papers, labs, and topics across Lattice.
Neural Field Thermal Tomography (NeFTY) is introduced as a differentiable physics framework for reconstructing 3D material properties from transient surface temperature data. It parameterizes the 3D diffusivity field as a continuous neural field and optimizes it using a rigorous numerical solver, enforcing thermodynamic laws as hard constraints. The discretize-then-optimize approach mitigates spectral bias and ill-posedness, leading to improved accuracy in subsurface defect localization compared to traditional methods and PINNs.
Differentiable physics enables high-resolution 3D tomography of subsurface defects by enforcing thermodynamic laws as hard constraints, outperforming traditional methods and PINNs.
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/
