SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution
About
State space models (SSMs) have emerged as a powerful paradigm for efficient single-image super-resolution (SR) due to their linear complexity and long-range modeling capabilities. However, existing Mamba-based methods typically rely on data-agnostic rigid scanning, which reshapes 2D images into 1D sequences over a fixed grid, inevitably disrupting spatial-semantic topology and introducing artifacts. Inspired by the \textbf{Gestalt perceptual grouping theory}, we propose \textbf{SP-MoMamba}, a superpixel-driven mixture of state space experts designed for content-aware SR. Our core idea is to transform the traditional rigid scanning into a \textbf{semantic-level interaction} by treating superpixels as fundamental units. Specifically, we introduce the \textbf{Superpixel-driven State Space Model (SP-SSM)}, which compresses semantically homogeneous regions into high-order tokens to preserve global topological consistency. To address the conflict between fixed scanning scales and diverse semantic granularities, we develop the \textbf{Multi-Scale Superpixel Mixture of State Space Experts (MSS-MoE)}. This module utilizes a dynamic routing mechanism to adaptively assign scale-specific experts, effectively capturing multi-scale textures while reducing computational redundancy. Furthermore, to prevent the loss of high-frequency details during global abstraction, we introduce a \textbf{Local Spatial Modulation Expert (LSME)} to complement the global modeling, ensuring a precise reconstruction of sharp edges and fine structures. Extensive experiments on standard benchmarks demonstrate that SP-MoMamba achieves superior reconstruction fidelity and a more favorable efficiency-performance trade-off compared to state-of-the-art efficient SR methods.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Super-resolution | Manga109 | PSNR39.76 | 875 | |
| Image Super-resolution | Set5 | PSNR38.16 | 774 | |
| Image Super-resolution | Set14 | PSNR33.81 | 565 | |
| Super-Resolution | Manga109 | PSNR31.51 | 368 | |
| Image Super-resolution | Urban100 x4 (test) | PSNR26.86 | 309 | |
| Low-light Image Enhancement | LOL real v2 (test) | PSNR23.82 | 150 | |
| JPEG artifact reduction | LIVE1 | PSNR34.78 | 142 | |
| Image Super-resolution | Urban100 x2 (test) | PSNR33.17 | 118 | |
| Image Super-resolution | Urban100 x3 (test) | PSNR28.96 | 96 | |
| Image Super-resolution | Manga109 x2 (test) | PSNR40.35 | 92 |