An Omni-Dimensional Dynamic Convolutional Network for Single-Image Super-Resolution Tasks

Xi Chen, Ziang Wu, Weiping Zhang, Tingting Bi and Chunwei Tian ()
Additional contact information
Xi Chen: School of Software, Northwestern Polytechnical University, Xi’an 710129, China
Ziang Wu: School of Software, Northwestern Polytechnical University, Xi’an 710129, China
Weiping Zhang: School of Software, Northwestern Polytechnical University, Xi’an 710129, China
Tingting Bi: School of Computing and Information Systems, University of Melbourne, Parkville 3010, Australia
Chunwei Tian: Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen 518057, China

Mathematics, 2025, vol. 13, issue 15, 1-21

Abstract: The goal of single-image super-resolution (SISR) tasks is to generate high-definition images from low-quality inputs, with practical uses spanning healthcare diagnostics, aerial imaging, and surveillance systems. Although cnns have considerably improved image reconstruction quality, existing methods still face limitations, including inadequate restoration of high-frequency details, high computational complexity, and insufficient adaptability to complex scenes. To address these challenges, we propose an Omni-dimensional Dynamic Convolutional Network (ODConvNet) tailored for SISR tasks. Specifically, ODConvNet comprises four key components: a Feature Extraction Block (FEB) that captures low-level spatial features; an Omni-dimensional Dynamic Convolution Block (DCB), which utilizes a multidimensional attention mechanism to dynamically reweight convolution kernels across spatial, channel, and kernel dimensions, thereby enhancing feature expressiveness and context modeling; a Deep Feature Extraction Block (DFEB) that stacks multiple convolutional layers with residual connections to progressively extract and fuse high-level features; and a Reconstruction Block (RB) that employs subpixel convolution to upscale features and refine the final HR output. This mechanism significantly enhances feature extraction and effectively captures rich contextual information. Additionally, we employ an improved residual network structure combined with a refined Charbonnier loss function to alleviate gradient vanishing and exploding to enhance the robustness of model training. Extensive experiments conducted on widely used benchmark datasets, including DIV2K, Set5, Set14, B100, and Urban100, demonstrate that, compared with existing deep learning-based SR methods, our ODConvNet method improves Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and the visual quality of SR images is also improved. Ablation studies further validate the effectiveness and contribution of each component in our network. The proposed ODConvNet offers an effective, flexible, and efficient solution for the SISR task and provides promising directions for future research.

Keywords: single image super-resolution; omni-dimensional dynamic convolution; residual networks; Charbonnier loss (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/2227-7390/13/15/2388/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/15/2388/ (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:2388-:d:1709732

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 ().