Physics guided method improves radar image generation for underground detection
PCFlow: Physics-Conditioned Flow Matching for GPR B-Scan Image Synthesis
Machine Learning
Summary
Creating realistic images from radar scans underground helps in testing and training new technologies, but it is hard to make these images both look right and follow physical rules. The researchers developed a method called PCFlow that uses physics knowledge about materials and shapes to guide how these images are made. This approach helps link the physical underground scene with the radar images more accurately. Tests showed that PCFlow produces images that are both visually good and physically meaningful, improving the reliability of simulated radar data.
ground-penetrating radarB-scan imagedata augmentationflow matchingMaxwell equationselectromagnetic simulationlatent spaceconditional generationgprMaxradargram synthesis
Authors
Zhijie Shen, Chenchen Fu, Xuanhao Chang, Hongtao Bai, Lili He
Abstract
Ground-penetrating radar (GPR) B-scan image synthesis is important for data augmentation, algorithm validation, and simulation acceleration, yet generating radargrams with both visual realism and physical consistency remains challenging. Existing learning-based generative models often emphasize visual appearance but provide limited control over response geometry. In this paper, we propose PCFlow, a physics-conditioned flow matching framework for fast GPR B-scan image synthesis. The core of PCFlow is a Maxwell-informed dense physical condition field constructed from the parameterized physical model used for electromagnetic simulation, including material properties, target geometry, propagation cues, and response-domain priors. This condition field provides an interpretable interface between physical scene parameters and radar response geometry, and guides conditional flow matching in the VAE latent space toward physically feasible generation paths. We evaluate PCFlow on a gprMax-based buried-pipeline dataset with both in-distribution and out-of-distribution test cases. Experimental results show that PCFlow generates images with more accurate response geometry and high visual fidelity, demonstrating its effectiveness for controllable and physically faithful radar image synthesis.