Self-Supervised Dual-Frequency Phase Decomposition for Single-Shot Composite Fringe Projection Profilometry

2026-06-18

AI Summary

This work addresses the limitations of conventional Fourier-based methods in single-shot fringe projection profilometry, which suffer from limited accuracy, and circumvents the need for costly phase or depth labels required by supervised learning approaches. It introduces, for the first time, a self-supervised learning framework for dual-frequency phase unwrapping that operates without ground-truth labels. The method models the scale and directional relationships between high- and low-frequency phase gradients and incorporates a soft edge-consistency loss to preserve object boundaries and fine geometric details. Experimental results demonstrate that, under fully unsupervised conditions, the proposed approach outperforms state-of-the-art transform-domain methods, achieving a mean absolute error (MAE_z) of 0.367 mm and a root mean square error (RMSE_z) of 1.804 mm, while increasing the ratio of valid pixels to 95.07%.

Abstract

Single-shot fringe projection profilometry (FPP) has been actively studied for real-time measurement, dynamic object reconstruction, and motion-sensitive environments. Composite fringe patterns are advantageous in single-shot FPP because multiple frequency components can be encoded in a single pattern, enabling phase ambiguity resolution. Existing approaches mainly rely on Fourier transform-based methods or supervised deep learning methods. However, Fourier transform-based methods often suffer from limited accuracy and degraded performance in complex regions, while supervised methods require dense phase or depth labels, which are costly to obtain. In this work, we propose a self-supervised phase refinement framework for single-shot composite fringe patterns without requiring phase or depth labels. The proposed method exploits the scale and direction relationships between low- and high-frequency phase gradients, improving the reliability of phase separation. We also introduce a soft edge consistency loss to preserve object boundaries and fine geometric structures. Experimental results show that the proposed method achieves MAE_z and RMSE_z of 0.367 mm and 1.804 mm, respectively, outperforming the best-performing transform-based baseline, which obtains 0.402 mm and 2.785 mm. The proposed method also improves the valid-pixel ratio from 84.75 % to 95.07 %. These results demonstrate the effectiveness of self-supervised dual-frequency phase refinement for reliable single-shot 3D reconstruction without ground-truth label supervision.

Problem

• single-shot FPP
• composite fringe
• phase decomposition
• self-supervised
• 3D reconstruction

Innovation

• self-supervised learning
• dual-frequency phase decomposition
• single-shot FPP
• phase refinement
• edge consistency loss