Adaptive Structured-Light 3D Surface Imaging with Cross-Domain Learning (Laser Photonics Rev. 19(12)/2025)

Enhancing Structured-Light 3D Imaging

A cross-domain learning framework for adaptive structured-light 3D imaging is proposed by Shijie Feng, Qian Chen, Chao Zuo, and co-workers in article number 2401609; it enhances generalization across diverse systems and environments. The method incorporates a mixture-of-experts architecture, significantly improving performance over traditional specialist and generalist DNNs, and advancing robust AI-driven optical metrology.