Reproduce “Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tao Zhong, Yixun Hu, Dongzhe Zheng, Aditya Sood, Christine Allen-Blanchette
NeFTY reconstructs hidden defect structure from pulsed-thermography surface measurements by proposing a diffusivity field, simulating heat with a physics-constrained solver, and updating the field to match camera data. On 1,000 synthetic samples, it achieves volumetric IoU 0.45 ± 0.04, versus 0.04 ± 0.02 for Grid Opt. Real PVC results cover projected masks and depth labels, not verified 3D recovery.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.