Double-Shot 3D Shape Measurement with a Dual-Branch Network for Structured Light Projection Profilometry

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lei, Mingyang, Fan, Jingfan, Shao, Long, Song, Hong, Xiao, Deqiang, Ai, Danni, Fu, Tianyu, Gu, Ying, Yang, Jian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916514901262336
author Lei, Mingyang
Fan, Jingfan
Shao, Long
Song, Hong
Xiao, Deqiang
Ai, Danni
Fu, Tianyu
Gu, Ying
Yang, Jian
author_facet Lei, Mingyang
Fan, Jingfan
Shao, Long
Song, Hong
Xiao, Deqiang
Ai, Danni
Fu, Tianyu
Gu, Ying
Yang, Jian
contents The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection profilometry (SPP) are two popular methods. However, they generally use a single projection pattern for reconstruction, resulting in fringe order ambiguity or poor reconstruction accuracy. To alleviate these problems, we propose a parallel dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet), to take advantage of convolutional operations and self-attention mechanisms for processing different SL modalities. Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images. To fully integrate complementary features, we design a double-stream attention aggregation module (DAAM) that consists of a parallel attention subnetwork for aggregating multi-scale spatial structure information. This module can dynamically retain local and global representations to the maximum extent. Moreover, an adaptive mixture density head with bimodal Gaussian distribution is proposed for learning a representation that is precise near discontinuities. Compared to the standard disparity regression strategy, this adaptive mixture head can effectively improve performance at object boundaries. Extensive experiments demonstrate that our method can reduce fringe order ambiguity while producing high-accuracy results on self-made datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14198
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Double-Shot 3D Shape Measurement with a Dual-Branch Network for Structured Light Projection Profilometry
Lei, Mingyang
Fan, Jingfan
Shao, Long
Song, Hong
Xiao, Deqiang
Ai, Danni
Fu, Tianyu
Gu, Ying
Yang, Jian
Computer Vision and Pattern Recognition
Image and Video Processing
The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection profilometry (SPP) are two popular methods. However, they generally use a single projection pattern for reconstruction, resulting in fringe order ambiguity or poor reconstruction accuracy. To alleviate these problems, we propose a parallel dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet), to take advantage of convolutional operations and self-attention mechanisms for processing different SL modalities. Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images. To fully integrate complementary features, we design a double-stream attention aggregation module (DAAM) that consists of a parallel attention subnetwork for aggregating multi-scale spatial structure information. This module can dynamically retain local and global representations to the maximum extent. Moreover, an adaptive mixture density head with bimodal Gaussian distribution is proposed for learning a representation that is precise near discontinuities. Compared to the standard disparity regression strategy, this adaptive mixture head can effectively improve performance at object boundaries. Extensive experiments demonstrate that our method can reduce fringe order ambiguity while producing high-accuracy results on self-made datasets.
title Double-Shot 3D Shape Measurement with a Dual-Branch Network for Structured Light Projection Profilometry
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2407.14198