First-order State Space Model for Lightweight Image Super-resolution
This work addresses the need for efficient super-resolution models in vision applications, though it is incremental as it builds on existing Mamba-based approaches.
The authors tackled the problem of improving lightweight image super-resolution by modifying the state space model (SSM) calculation process without adding parameters, resulting in enhanced performance that surpasses current lightweight methods and achieves state-of-the-art results on five benchmark datasets.
State space models (SSMs), particularly Mamba, have shown promise in NLP tasks and are increasingly applied to vision tasks. However, most Mamba-based vision models focus on network architecture and scan paths, with little attention to the SSM module. In order to explore the potential of SSMs, we modified the calculation process of SSM without increasing the number of parameters to improve the performance on lightweight super-resolution tasks. In this paper, we introduce the First-order State Space Model (FSSM) to improve the original Mamba module, enhancing performance by incorporating token correlations. We apply a first-order hold condition in SSMs, derive the new discretized form, and analyzed cumulative error. Extensive experimental results demonstrate that FSSM improves the performance of MambaIR on five benchmark datasets without additionally increasing the number of parameters, and surpasses current lightweight SR methods, achieving state-of-the-art results.