SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution

arXiv:2605.25892 · cs.CV · Submitted 2026-05-25 · Read on arXiv

cs.CV

Submitted: 2026-05-25

Updated: 2026-09-18

Terminology

• Transformer — 28× in this paper · explained in 2 episodes
• State Space Model — 17× in this paper
• Computer Vision and Pattern Recognition — 15× in this paper
• Benchmark — 11× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Fidelity — 7× in this paper · explained in 2 episodes
• Mixture of Experts — 6× in this paper · explained in 2 episodes
• Redundancy — 6× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• State Space Models (SSMs) — 5× in this paper · explained in 4 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Attention Mechanism — 4× in this paper · explained in 3 episodes
• Clustering — 4× in this paper · explained in 2 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Local Mixed Attention — 4× in this paper
• Superpixel Global Modulating Expert — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Activation Function — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Continual Learning — 3× in this paper · explained in 2 episodes
• Layers of Experts — 3× in this paper
• Local Spatial Modulation Expert — 3× in this paper
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition Workshops — 2× in this paper
• Diffusion Index — 2× in this paper
• Mixture of Experts (MoE) — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Convolutional Neural Networks (CNNs) — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Ensemble Approach — 1× in this paper · explained in 3 episodes
• Local Attribution Maps — 1× in this paper
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Multimodal Learning — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Swin MHSA and Channel Attention — 1× in this paper
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• VMamba: Visual State Space Model
• Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
• Mamba YOLO: A Simple Baseline for Object Detection with State Space Model
• Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution
• FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining
• Accurate Image Restoration with Attention Retractable Transformer
• Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
• Residual Mixture of Experts
• GLU Variants Improve Transformer
• Categorical Reparameterization with Gumbel-Softmax
• Adam: A Method for Stochastic Optimization
• Vision Transformer with Super Token Sampling
• Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement
• HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement
• Residual Non-local Attention Networks for Image Restoration
• Deep Retinex Decomposition for Low-Light Enhancement

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models