First-order State Space Model for Lightweight Image Super-resolution

2025-09-10

AI Summary

To address the limited modeling capacity and parameter sensitivity of state space models (SSMs) in lightweight image super-resolution, this paper proposes the First-order State Space Model (FSSM). The core innovation lies in introducing a first-order preservation condition to derive a novel discretization scheme with low cumulative error, while explicitly modeling inter-token correlations—thereby enhancing visual feature representation without increasing model parameters. FSSM is fully compatible with existing SSM-based architectures (e.g., MambaIR) as a drop-in replacement. Extensive experiments demonstrate that FSSM achieves state-of-the-art performance across five standard super-resolution benchmarks, consistently outperforming prior lightweight methods in both reconstruction quality and computational efficiency.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Enhancing lightweight image super-resolution performance
• Improving State Space Models without parameter increase
• Incorporating token correlations to surpass current methods

Innovation

• First-order State Space Model for SR
• Modified SSM calculation without extra parameters
• Incorporated token correlations to enhance performance