PCTNet: depth estimation from single structured light image with a parallel CNN-transformer network
Measurement Science and Technology · 01.08.2023 · 34 (8) · 085402
DOI: 10.1088/1361-6501/acd136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 10.05.2023. Verfasst von Xinjun Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Science & Technology Development Fund of Tianjin Education Commission for Higher Education, National Natural Science Foundation of China.
Abstract (Originalsprache)
Recent approaches based on convolutional neural networks significantly improve the performance of structured light image depth estimation in fringe projection and speckle projection 3D measurement. However, it remains challenging to simultaneously preserve the global structure and local details of objects for the structured light images in complex scenes. In this paper, we design a parallel CNN-transformer network (PCTNet), which consists of a CNN branch, a transformer branch, a bidirectional feature fusion module (BFFM), and a cross-feature multi-scale fusion module (CFMS). The BFFM and CFMS modules are proposed to fuse local and global features of the double branches in order to achieve better depth estimation. Comprehensive experiments are conducted to evaluate our model on four structured light datasets, i.e. our established simulated fringe and speckle structured light datasets, and public real fringe and speckle structured light datasets. Experiments demonstrate that the proposed PCTNet is an effective architecture, achieving state-of-the-art performance in both qualitative and quantitative evaluation.
Förderung
- Science & Technology Development Fund of Tianjin Education Commission for Higher Education
- National Natural Science Foundation of China
Zitieren
APA
Zhu, X., Han, Z., Zhang, Z., Song, L., Wang, H., & Guo, Q. (2023). PCTNet: depth estimation from single structured light image with a parallel CNN-transformer network. Measurement Science and Technology, 34(8), 085402. https://doi.org/10.1088/1361-6501/acd136
Vancouver
Zhu X, Han Z, Zhang Z, Song L, Wang H, Guo Q. PCTNet: depth estimation from single structured light image with a parallel CNN-transformer network. Measurement Science and Technology. 2023;34(8):085402. doi:10.1088/1361-6501/acd136
BibTeX
@article{Zhu2023,
author = {Zhu, Xinjun and Han, Zhiqiang and Zhang, Zhizhi and Song, Limei and Wang, Hongyi and Guo, Qinghua},
title = {PCTNet: depth estimation from single structured light image with a parallel CNN-transformer network},
journal = {Measurement Science and Technology},
year = {2023},
volume = {34},
number = {8},
pages = {085402},
doi = {10.1088/1361-6501/acd136}
}
EUVIMED