ST-GVMNet: a structure-texture dual-stream network fusing gating mechanism and V-Mamba for Dunhuang mural image inpainting
Journal of King Saud University Computer and Information Sciences · 2026-08 · 38 (6)
DOI: 10.1007/s44443-026-00858-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 27.05.2026. Verfasst von Rui Tian und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Nature Science Foundation of China, "Innovation Star" Program for Excellent Graduate Students of Gansu Province, Gansu Province Excellent Doctoral Student Project.
Abstract (Originalsprache)
Dunhuang murals are afflicted by complex degradation phenomena, including extensive content loss, blurred textures, and pervasive mould-spot corrosion. Existing image inpainting methods often fail to handle these intricate degradation patterns effectively, primarily due to their limited ability to model long-range dependencies, susceptibility to structural flow noise, and inability to preserve high-frequency details. To address these challenges, we propose ST-GVMNet, a Structure-Texture Dual-Stream Network that synergistically integrates Gating Mechanisms with the Visual Mamba (V-Mamba) architecture for Dunhuang mural inpainting. Adopting a coarse-to-fine, decoupled strategy, the network consists of two core components: a Structure Reconstruction Network (SRN) and a Texture Refinement Network (TRN). In the SRN stage, we develop a Structure Gate Fusion Module (SGFM) to adaptively filter structural features and suppress edge noise through spatially weighted gating operations. For texture inpainting, we introduce a Multi-scale Dilated VMamba (MD-VMamba) module, which leverages 2D selective scanning and dilated feedforward blocks to capture both global contextual information and fine-grained local details. Furthermore, a Variance-Gated Aggregation Module (VGAM) is proposed to dynamically recover high-frequency nuances by utilizing local variance as a saliency indicator. Extensive experiments on the Dunhuang mural and Thangka datasets, as well as standard benchmarks, demonstrate that ST-GVMNet achieves state-of-the-art (SOTA) performance in both quantitative metrics and qualitative visual fidelity. Notably, our method exhibits exceptional structural coherence and robustness when inpainting images under extreme mask ratios.
Förderung
- National Nature Science Foundation of China
- "Innovation Star" Program for Excellent Graduate Students of Gansu Province
- Gansu Province Excellent Doctoral Student Project
Zitieren
APA
Tian, R., Wu, T., Feng, D., Wang, L., & Xin, Z. (2026). ST-GVMNet: a structure-texture dual-stream network fusing gating mechanism and V-Mamba for Dunhuang mural image inpainting. Journal of King Saud University Computer and Information Sciences, 38(6). https://doi.org/10.1007/s44443-026-00858-5
Vancouver
Tian R, Wu T, Feng D, Wang L, Xin Z. ST-GVMNet: a structure-texture dual-stream network fusing gating mechanism and V-Mamba for Dunhuang mural image inpainting. Journal of King Saud University Computer and Information Sciences. 2026;38(6). doi:10.1007/s44443-026-00858-5
BibTeX
@article{Tian2026,
author = {Tian, Rui and Wu, Tongchen and Feng, Dandan and Wang, Lulu and Xin, Zihao},
title = {ST-GVMNet: a structure-texture dual-stream network fusing gating mechanism and V-Mamba for Dunhuang mural image inpainting},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {6},
doi = {10.1007/s44443-026-00858-5}
}
EUVIMED