{"ID":2845674,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.03232","arxiv_id":"2511.03232","title":"Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution","abstract":"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.","short_abstract":"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 scale...","url_abs":"https://arxiv.org/abs/2511.03232","url_pdf":"https://arxiv.org/pdf/2511.03232v2","authors":"[\"Sichen Guo\",\"Wenjie Li\",\"Yuanyang Liu\",\"Guangwei Gao\",\"Jian Yang\",\"Chia-Wen Lin\"]","published":"2025-11-05T06:46:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}