Poster + Paper
22 November 2024 Single-frame structured light depth map reconstruction with absolute phase-aided supervision
Mingfeng Chen, YiMing Li, Xinghui Li, Xiaojun Liang, Zinan Li, Weikang Chen, Hao Wang, ChaoBo Zhang, Xiaohao Wang, WeiHua Gui
Author Affiliations +
Conference Poster
Abstract
In recent years, end-to-end depth map prediction from single-shot fringe modulation images in structured light 3D measurement(F2D) has drawn widespread attention, which has significantly reduced measurement times and eliminated the complex intermediate steps in the traditional method. However, F2D is a long-distance ill-conditioned prediction problem, and it is difficult for existing regression networks to achieve high-precision pixel-by-pixel prediction over long distances in space and time. For the challenge, we propose APS-UNet(Absolute Phase aided Supervision UNet), an endto- end depth maps prediction network supervised by an absolute phase branch. With the core physical process, absolute phase branch as auxiliary supervision, can decompose the one challenging long-distance prediction into two easier shortdistance prediction tasks. Moreover, in the training process, the two branches provide feedback to each other, enhancing the accuracy and robustness of depth prediction. Compared to Res-UNet, APS-UNet demonstrates a 32% decrease in mean absolute error (MAE) based on the real dataset, highlighting the effectiveness of this network.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Mingfeng Chen, YiMing Li, Xinghui Li, Xiaojun Liang, Zinan Li, Weikang Chen, Hao Wang, ChaoBo Zhang, Xiaohao Wang, and WeiHua Gui "Single-frame structured light depth map reconstruction with absolute phase-aided supervision", Proc. SPIE 13239, Optoelectronic Imaging and Multimedia Technology XI, 132390P (22 November 2024); https://doi.org/10.1117/12.3035560
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Depth maps

Structured light

Education and training

3D image processing

Fringe analysis

Lithium

Phase reconstruction

Back to Top