Image Inpainting Algorithm Based on Structure-Guided Generative Adversarial Network

Li Zhao, Tongyang Zhu (), Chuang Wang, Feng Tian and Hongge Yao
Additional contact information
Li Zhao: School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China
Tongyang Zhu: School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China
Chuang Wang: School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China
Feng Tian: Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan 215316, China
Hongge Yao: School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710064, China

Mathematics, 2025, vol. 13, issue 15, 1-25

Abstract: To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) framework that hierarchically integrates structural priors with semantic-aware texture synthesis. The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. The framework introduces three innovations: (1) a hierarchical feature fusion architecture that synergizes multi-scale receptive fields with spatial-channel attention to preserve long-range dependencies and local details simultaneously; (2) spectral-normalized Markovian discriminator with gradient-penalty regularization, enabling adversarial training stability while enforcing patch-level structural consistency; and (3) dual-branch loss formulation combining perceptual similarity metrics with edge-aware constraints to align synthesized content with both semantic coherence and geometric fidelity. Our experiments on the two benchmark datasets (Places2 and CelebA) have demonstrated that our framework achieves more unified textures and structures, bringing the restored images closer to their original semantic content.

Keywords: image inpainting; structural prior guidance; generative adversarial networks; multi-scale attention; spectral normalization; deep learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/15/2370/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/15/2370/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:15:p:2370-:d:1708789

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().