UMSPU: Universal Multi-Size Phase Unwrapping via Mutual Self-Distillation and Adaptive Boosting Ensemble Segmenters
This work addresses a domain-specific problem in industrial measurement by providing a universal solution for phase unwrapping, though it appears incremental as it builds on deep learning methods with novel mechanisms.
The paper tackles the problem of spatial phase unwrapping for 3D morphology extraction in industrial measurement, where existing methods struggle with noise resistance, speed, and handling large image sizes; the proposed UMSPU network achieves high precision across image sizes from 256*256 to 2048*2048 (an 8 times increase) and outperforms existing methods in speed, robustness, and generalization.
Spatial phase unwrapping is a key technique for extracting phase information to obtain 3D morphology and other features. Modern industrial measurement scenarios demand high precision, large image sizes, and high speed. However, conventional methods struggle with noise resistance and processing speed. Current deep learning methods are limited by the receptive field size and sparse semantic information, making them ineffective for large size images. To address this issue, we propose a mutual self-distillation (MSD) mechanism and adaptive boosting ensemble segmenters to construct a universal multi-size phase unwrapping network (UMSPU). MSD performs hierarchical attention refinement and achieves cross-layer collaborative learning through bidirectional distillation, ensuring fine-grained semantic representation across image sizes. The adaptive boosting ensemble segmenters combine weak segmenters with different receptive fields into a strong one, ensuring stable segmentation across spatial frequencies. Experimental results show that UMSPU overcomes image size limitations, achieving high precision across image sizes ranging from 256*256 to 2048*2048 (an 8 times increase). It also outperforms existing methods in speed, robustness, and generalization. Its practicality is further validated in structured light imaging and InSAR. We believe that UMSPU offers a universal solution for phase unwrapping, with broad potential for industrial applications.