XTNSR: Xception-based transformer network for single image super resolution
Abstract Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01760-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861498100842496 |
|---|---|
| author | Jagrati Talreja Supavadee Aramvith Takao Onoye |
| author_facet | Jagrati Talreja Supavadee Aramvith Takao Onoye |
| author_sort | Jagrati Talreja |
| collection | DOAJ |
| description | Abstract Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches. This paper presents a Deep Learning model for single-image super-resolution. In this paper, we present the XTNSR model, a novel multi-path network architecture that combines Local feature window transformers (LWFT) with Xception blocks for single-image super-resolution. The model processes grid-like image patches effectively and reduces computational complexity by integrating a Patch Embedding layer. Whereas the Xception blocks use depth-wise separable convolutions for hierarchical feature extraction, the LWFT blocks capture long-range dependencies and fine-grained qualities. A multi-layer feature fusion block with skip connections, part of this hybrid architecture, guarantees efficient local and global feature fusion. The experimental results show better performance in Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual quality than the state-of-the-art techniques. By optimizing parameters, the suggested architecture also lowers computational complexity. Overall, the architecture presents a promising approach for advancing image super-resolution capabilities. |
| format | Article |
| id | doaj-art-bd4a1555b99d4f6ebd200c1d6f318ee9 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-bd4a1555b99d4f6ebd200c1d6f318ee92025-02-09T13:01:16ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111212510.1007/s40747-024-01760-1XTNSR: Xception-based transformer network for single image super resolutionJagrati Talreja0Supavadee Aramvith1Takao Onoye2Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityMultimedia Data Analytics and Processing Unit, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityGraduate School of Information Science and Technology, Osaka UniversityAbstract Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches. This paper presents a Deep Learning model for single-image super-resolution. In this paper, we present the XTNSR model, a novel multi-path network architecture that combines Local feature window transformers (LWFT) with Xception blocks for single-image super-resolution. The model processes grid-like image patches effectively and reduces computational complexity by integrating a Patch Embedding layer. Whereas the Xception blocks use depth-wise separable convolutions for hierarchical feature extraction, the LWFT blocks capture long-range dependencies and fine-grained qualities. A multi-layer feature fusion block with skip connections, part of this hybrid architecture, guarantees efficient local and global feature fusion. The experimental results show better performance in Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual quality than the state-of-the-art techniques. By optimizing parameters, the suggested architecture also lowers computational complexity. Overall, the architecture presents a promising approach for advancing image super-resolution capabilities.https://doi.org/10.1007/s40747-024-01760-1Single image super-resolutionLocal feature window transformer blockMulti-layer feature fusion blockXception block |
| spellingShingle | Jagrati Talreja Supavadee Aramvith Takao Onoye XTNSR: Xception-based transformer network for single image super resolution Complex & Intelligent Systems Single image super-resolution Local feature window transformer block Multi-layer feature fusion block Xception block |
| title | XTNSR: Xception-based transformer network for single image super resolution |
| title_full | XTNSR: Xception-based transformer network for single image super resolution |
| title_fullStr | XTNSR: Xception-based transformer network for single image super resolution |
| title_full_unstemmed | XTNSR: Xception-based transformer network for single image super resolution |
| title_short | XTNSR: Xception-based transformer network for single image super resolution |
| title_sort | xtnsr xception based transformer network for single image super resolution |
| topic | Single image super-resolution Local feature window transformer block Multi-layer feature fusion block Xception block |
| url | https://doi.org/10.1007/s40747-024-01760-1 |
| work_keys_str_mv | AT jagratitalreja xtnsrxceptionbasedtransformernetworkforsingleimagesuperresolution AT supavadeearamvith xtnsrxceptionbasedtransformernetworkforsingleimagesuperresolution AT takaoonoye xtnsrxceptionbasedtransformernetworkforsingleimagesuperresolution |