.png){kind=icon}
返回
TTFDNet: Precise Depth Estimation from Single-Frame Fringe Patterns
.png){kind=icon}
OA
AI
DOI：10.3390/s24144733.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This work presents TTFDNet, a trans;
mer-based and transfer learning network;
end-to-end depth estimation from single-frame fringe patterns in fringe projection profilometry. TTFDNet features a precise contour and coarse depth (PCCD) pre-processor, a global multi-dimensional fusion (GMDF) module and a progressive depth extractor (PDE). It utilizes transfer learning through fringe structure consistency evaluation (FSCE) to leverage the trans;
mer's benefits even on a small dataset. Tested on 208 scenes, the model achieved a mean absolute error (MAE) of 0.00372 mm, outperforming Unet (0.03458 mm) models, PDE (0.01063 mm) and PCTNet (0.00518 mm). It demonstrated precise measurement capabilities with deviations of similar to 90 mu m for a 25.4 mm radius ball and similar to 6 mu m for a 20 mm thick metal part. Additionally, TTFDNet showed excellent generalization and robustness in dynamic reconstruction and varied imaging conditions, making it appropriate for practical applications in manufacturing, automation and computer vision.
Keyword:
fringe projection profilometry
depth estimation
deep learning
transfer learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Absolute phase retrieval based on fringe amplitude encoding without any additional auxiliary pattern.png)
OPTICS EXPRESS
OAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏分享收藏Three-dimensional Shape Reconstruction from Single-shot Speckle Image Using Deep Convolutional Neural Networks基于深度卷积神经网络的单镜头散斑图像三维形状重建
PREAI
分享收藏分享收藏Motion induced error reduction methods for phase shifting profilometry: A review相移轮廓术的运动诱导误差减小方法: 综述
PREAI
分享收藏
查看更多内容