Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915951328362496 |
|---|---|
| author | Guo, Sichen Li, Wenjie Liu, Yuanyang Gao, Guangwei Yang, Jian Lin, Chia-Wen |
| author_facet | Guo, Sichen Li, Wenjie Liu, Yuanyang Gao, Guangwei Yang, Jian Lin, Chia-Wen |
| contents | Recently, Mamba-based super-resolution (SR) methods have demonstrated the ability to capture global receptive fields with linear complexity, addressing the quadratic computational cost of Transformer-based SR approaches. However, existing Mamba-based methods lack fine-grained transitions across different modeling scales, which limits the efficiency of feature representation. In this paper, we propose T-PMambaSR, a lightweight SR framework that integrates window-based self-attention with Progressive Mamba. By enabling interactions among receptive fields of different scales, our method establishes a fine-grained modeling paradigm that progressively enhances feature representation without introducing additional computational cost. Furthermore, we introduce an Adaptive High-Frequency Refinement Module (AHFRM) to recover high-frequency details lost during Transformer and Mamba processing. Extensive experiments demonstrate that T-PMambaSR progressively enhances the model's receptive field and expressiveness, yielding better performance than recent Transformer- or Mamba-based methods while incurring lower computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution Guo, Sichen Li, Wenjie Liu, Yuanyang Gao, Guangwei Yang, Jian Lin, Chia-Wen Computer Vision and Pattern Recognition Recently, Mamba-based super-resolution (SR) methods have demonstrated the ability to capture global receptive fields with linear complexity, addressing the quadratic computational cost of Transformer-based SR approaches. However, existing Mamba-based methods lack fine-grained transitions across different modeling scales, which limits the efficiency of feature representation. In this paper, we propose T-PMambaSR, a lightweight SR framework that integrates window-based self-attention with Progressive Mamba. By enabling interactions among receptive fields of different scales, our method establishes a fine-grained modeling paradigm that progressively enhances feature representation without introducing additional computational cost. Furthermore, we introduce an Adaptive High-Frequency Refinement Module (AHFRM) to recover high-frequency details lost during Transformer and Mamba processing. Extensive experiments demonstrate that T-PMambaSR progressively enhances the model's receptive field and expressiveness, yielding better performance than recent Transformer- or Mamba-based methods while incurring lower computational cost. |
| title | Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.03232 |