EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep Learning Framework with Multi-Scale Texture Enhancement and Heatmap Fusion for Face Super Resolution

Bing Xu, Lei Wang, Yanxia Wu, Xiaoming Liu, Lu Gan

AI · 09.01.2026 · 7 (1) · 20

DOI: 10.3390/ai7010020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 09.01.2026. Verfasst von Bing Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Anhui Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Face super-resolution (FSR) has made great progress thanks to deep learning and facial priors. However, many existing methods do not fully exploit landmark heatmaps and lack effective multi-scale texture modeling, which often leads to texture loss and artifacts under large upscaling factors. To address these problems, we propose a Multi-Scale Residual Stacking Network (MRSNet), which integrates multi-scale texture enhancement with multi-stage heatmap fusion. The MRSNet is built upon Residual Attention-Guided Units (RAGUs) and incorporates a Face Detail Enhancer (FDE), which applies edge, texture, and region branches to achieve differentiated enhancement across facial components. Furthermore, we design a Multi-Scale Texture Enhancement Module (MTEM) that employs progressive average pooling to construct hierarchical receptive fields and employs heatmap-guided attention for adaptive texture refinement. In addition, we introduce a multi-stage heatmap fusion strategy that injects landmark priors into multiple phases of the network, including feature extraction, texture enhancement, and detail reconstruction, enabling deep sharing and progressive integration of prior knowledge. Extensive experiments on CelebA and Helen demonstrate that the proposed method achieves superior detail recovery and generates perceptually realistic high-resolution face images. Both quantitative and qualitative evaluations confirm that our approach outperforms state-of-the-art methods.

Förderung

  • Natural Science Foundation of Anhui Province
  • National Natural Science Foundation of China

Zitieren

APA

Xu, B., Wang, L., Wu, Y., Liu, X., & Gan, L. (2026). A Deep Learning Framework with Multi-Scale Texture Enhancement and Heatmap Fusion for Face Super Resolution. AI, 7(1), 20. https://doi.org/10.3390/ai7010020

Vancouver

Xu B, Wang L, Wu Y, Liu X, Gan L. A Deep Learning Framework with Multi-Scale Texture Enhancement and Heatmap Fusion for Face Super Resolution. AI. 2026;7(1):20. doi:10.3390/ai7010020

BibTeX
@article{Xu2026,
  author = {Xu, Bing and Wang, Lei and Wu, Yanxia and Liu, Xiaoming and Gan, Lu},
  title = {A Deep Learning Framework with Multi-Scale Texture Enhancement and Heatmap Fusion for Face Super Resolution},
  journal = {AI},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {20},
  doi = {10.3390/ai7010020}
}
Kostenlos starten →