计算机科学
相互信息
混叠
人工智能
反射(计算机编程)
一般化
计算机视觉
忠诚
深度学习
模式识别(心理学)
光学
物理
电信
数学分析
数学
欠采样
程序设计语言
作者
Lei Lü,Yuejiao Guo,Zhilong Su,Qinghui Zhang,Dongsheng Zhang,Peng Li
出处
期刊:Optics Express
[Optica Publishing Group]
日期:2024-09-16
卷期号:32 (21): 36171-36171
摘要
Simultaneous structured light imaging of multiple objects has become more demanding and widely in many scenarios involving robot operations in intelligent manufacturing. However, it is challenged by pattern aliasing caused by mutual reflection between high-reflective objects. To this end, we propose to learn clear fringe patterns from aliased mutual-reflective observations by diffusion models for achieving high-fidelity multi-body reconstruction in line with typical phase-shift algorithms. Regarding mutual reflection imaging as a formation of adding significant noise, we build a supervised generative learning framework based on diffusion models and then train a self-attention-based deep network with a U-Net-like skip-connected encoder-decoder architecture. We demonstrate the generalization capability of the trained model in fringe pattern recovery and its performance in phase and three-dimensional (3D) shape reconstruction. Both experimental results show that the proposed method has the expected feasibility and accuracy, heralding a promising solution for addressing the current challenge in various multi-body mutual-reflective 3D reconstruction tasks.
科研通智能强力驱动
Strongly Powered by AbleSci AI