Phase unwrapping based on channel transformer U-Net for single-shot fringe projection profilometry

Sun, Gaowei; Li, Biyuan; Li, Zhuo; Wang, Xiuwei; Cai, Pengfei; Qie, Chaoyang

doi:10.1007/s12596-023-01515-0

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The need for employing a multi-frequency phase-shifting approach in the phase unwrapping process has driven the exploration of encoding diverse information into a composite pattern [25,[51][52][53][54]. Subsequently, the wrapped phase map can serve as either the input or output vector in co-operation between fringe projection and learning-based networks [55][56][57][58]. Recognizing the significance of the integer fringe orders in the phase unwrapping scheme, several methods have trained CNN models to segment the integer fringe orders or predict the coarse phase map [59][60][61][62].…”

Section: Related Workmentioning

confidence: 99%

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches

Nguyen,

Wang

2024

Sensors

View full text Add to dashboard Cite

The field of computer vision has been focusing on achieving accurate three-dimensional (3D) object representations from a single two-dimensional (2D) image through deep artificial neural networks. Recent advancements in 3D shape reconstruction techniques that combine structured light and deep learning show promise in acquiring high-quality geometric information about object surfaces. This paper introduces a new single-shot 3D shape reconstruction method that uses a nonlinear fringe transformation approach through both supervised and unsupervised learning networks. In this method, a deep learning network learns to convert a grayscale fringe input into multiple phase-shifted fringe outputs with different frequencies, which act as an intermediate result for the subsequent 3D reconstruction process using the structured-light fringe projection profilometry technique. Experiments have been conducted to validate the practicality and robustness of the proposed technique. The experimental results demonstrate that the unsupervised learning approach using a deep convolutional generative adversarial network (DCGAN) is superior to the supervised learning approach using UNet in image-to-image generation. The proposed technique’s ability to accurately reconstruct 3D shapes of objects using only a single fringe image opens up vast opportunities for its application across diverse real-world scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches

Nguyen,

Wang

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The model predicts wrap count or fringe order as output. Sun et al [27] proposed another architecture using a channel wise cross fusion transformer with UNET for phase unwrapping in single shot fringe projection profilometry. Zhao et al [28] have combined Swin Transformer with Zernike polynomial fitting for phase unwrapping.…”

Section: Introductionmentioning

confidence: 99%

Transformer based deep learning hybrid architecture for phase unwrapping

Bujagouni,

Pradhan

2024

Phys. Scr.

View full text Add to dashboard Cite

A deep learning Hybrid architecture for phase unwrapping has been proposed. The hybrid architecture is based on integration of Convolutional Neural Networks (CNN) with Vision Transformer. The performance of Hybrid architecture/network in phase unwrapping is compared against CNN based standard UNET network. Structural Similarity Index (SSIM) and Root Mean Square Error (RMSE) have been used as performance metrics to assess the performance of these deep learning networks for phase unwrapping. To train and test the networks, dataset with high mean Entropy has been generated using Gaussian filtering of random noise in Fourier plane. The Hybrid architecture is tested on test dataset and is found to have superior performance metrics against the UNET network. Their performance is also tested in noisy environment with various noise levels and Hybrid architecture demonstrated better anti-noise capability than UNET network. Hybrid architecture was successfully validated in real world scenario using experimental data from custom built Digital Holographic Microscope. With the advent of newer architectures and hardware, Deep learning networks can further improve the performance in solving inverse problems.

show abstract

Distortion correction algorithm based on absolute phase image in structured light 3D reconstruction

Feng,

Li,

Tao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

This paper proposed a distortion correction algorithm based on absolute phase image for structured light 3D measurement system composed of dual-projector and single camera. A pixel-based distortion error lookup table is established to compensate the distortion error. The absolute phase of the full field of view of the camera is obtained by the target plate, and the point cloud of the target plate is fitted as the reference plane. The distortion error lookup table is established to achieve high-precision 3D measurement. The experimental results show that: the structured light 3D measurement system not only expands the measurement range of the single projector-camera system, but also effectively correct and compensate the distortion of the captured point cloud. Compared with the accuracy without correction and compensation, the accuracy is improved by at least 95.7%. Through distortion correction and compensation, the warping phenomenon caused by distortion is effectively improved, and the problem of dual-projector point cloud fusion and stratification is overcome.

show abstract

Phase unwrapping based on channel transformer U-Net for single-shot fringe projection profilometry

Cited by 3 publications

References 26 publications

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches

Single-Shot 3D Reconstruction via Nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches

Transformer based deep learning hybrid architecture for phase unwrapping

Distortion correction algorithm based on absolute phase image in structured light 3D reconstruction

Contact Info

Product

Resources

About