U-Shaped Transformer Image Denoising Network with Decoder-Side Pre-Fusion Calibration
Applied Sciences · 04.05.2026 · 16 (9) · 4523
DOI: 10.3390/app16094523 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 04.05.2026. Verfasst von Peng Cui und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
U-shaped encoder-decoder architectures are widely adopted for image denoising due to their strong capability in multi-scale modeling. However, most existing methods still rely on relatively fixed encoder-decoder feature fusion strategies, which limit effective collaboration between encoder and decoder features. To address this issue, we propose a U-shaped Transformer image denoising network with decoder-side pre-fusion calibration (UT-DPFC). Built on a U-shaped Transformer backbone, UT-DPFC inserts Structure-Detail Candidate Attention (SDCA) before encoder-decoder feature fusion at three decoding stages to calibrate decoder features, thereby providing a more reliable basis for fusion and facilitating the effective use of injected detail cues during subsequent restoration. The Transformer architecture alternately adopts Window-based Multi-Head Self-Attention (W-MSA) and Shifted Window-based Multi-Head Self-Attention (SW-MSA), together with a Locally Enhanced Feed-forward Network (LeFF), to enhance local feature modeling. SDCA generates queries from the current decoder features and performs content-adaptive retrieval and aggregation over a complementary key-value candidate pool composed of Multi-Scale Region Candidates (MSRC) and Multi-Receptive-Field Pixel Candidates (MRPC), thereby calibrating decoder features before fusion. Extensive experiments show that UT-DPFC achieves favorable performance on synthetic Gaussian and real-world denoising. It performs better in heavy noise and complex textures, maintaining moderate inference cost.
Zitieren
APA
Cui, P., Meng, Q., & Gao, C. (2026). U-Shaped Transformer Image Denoising Network with Decoder-Side Pre-Fusion Calibration. Applied Sciences, 16(9), 4523. https://doi.org/10.3390/app16094523
Vancouver
Cui P, Meng Q, Gao C. U-Shaped Transformer Image Denoising Network with Decoder-Side Pre-Fusion Calibration. Applied Sciences. 2026;16(9):4523. doi:10.3390/app16094523
BibTeX
@article{Cui2026,
author = {Cui, Peng and Meng, Qinghan and Gao, Chuang},
title = {U-Shaped Transformer Image Denoising Network with Decoder-Side Pre-Fusion Calibration},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {9},
pages = {4523},
doi = {10.3390/app16094523}
}
EUVIMED