Ultra-efficient 3D shape reconstruction: Line-coded absolute phase unwrapping algorithm

• Published in: Pattern recognition Vol. 172; p. 112366
• Main Authors: An, Haihua, Cao, Yiping, Zhang, Hechen
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2026
• Subjects: Dynamic 3D shape reconstruction; Fringe mutual compensation; Fringe projection profilometry; Line-coded absolute phase unwrapping; Multi-layer decoding; Fringe mutual compensation; Multi-layer decoding; Dynamic 3D shape reconstruction; Fringe projection profilometry; Line-coded absolute phase unwrapping
• ISSN: 0031-3203
• DOI: 10.1016/j.patcog.2025.112366

•An ultra-efficient line-coded absolute phase unwrapping (LCAPU) algorithm is proposed for dynamic 3D shape reconstruction of the complex scene.•All line-coded phase-shifting patterns can compensate for each other and accurately participate in the extraction of wrapped phase.•No extra coded patterns are embedded into the projection sequence of the dynamic scene to destroy the dynamic coherence of adjacent phase-shifting patterns, thus suppressing the motion errors.•Multi-layer decoding (MLD) does not require the intricate error identification and artificial judgment conditions to perform fringe order correction.•Extensive experiments validate that this work has considerable performance in ultra-efficient and high-precision 3D reconstruction of the high-dynamic scene. Absolute phase unwrapping-based fringe projection profilometry (APU-FPP) has the advantages of pixel-wise calculation, high precision, and full-field sensing of 3D shape information. To the best of our knowledge, existing APU-FPP methods have a general contradiction between accuracy and efficiency because of projecting extra auxiliary coded fringes (ACFs). In this paper, a line-coded absolute phase unwrapping (LCAPU) algorithm is presented for absolute 3D shape reconstruction of the scene with non-uniform reflectivity and complex surfaces. Firstly, a sequence of single-pixel lines is successively embedded into two sets of 3-step phase-shifting patterns to mark fringe periods, which can thoroughly avoid extra ACFs to disrupt the coherence of adjacent morphological information. Secondly, two line-coded phase-shifting patterns with the same phase shift are used to recognize the corresponding coded lines containing the fringe order cue, which can be simultaneously used to guide fringe mutual compensation, thereby extracting a high-quality phase. Finally, according to the pixel positions and the fringe indices of the decoded lines, a multi-layer decoding (MLD) algorithm is developed to iteratively generate a fringe order map, which can adapt to the randomness of morphological changes. Compared to other methods, the proposed LCAPU can not only perform a one-shot 3D shape reconstruction with a single image acquisition, but also automatically correct phase errors, balancing ultra-efficiency and high accuracy. Experimental results demonstrate the superior performance and the practical application potential in dynamic complex scenes.