# An Efficient and Mixed Heterogeneous Model for Image Restoration arXiv: https://arxiv.org/abs/2504.10967 ยท HTML: https://mlsanity.com/paper/2504.10967/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba). - Builds on 38 of its 58 references that are in the map. - First posted on arXiv 15 Apr 2025. ## Placed in - State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/) ## Builds on (most cited first, 30 of 38) - [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023) - [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021) - [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021) - [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014) - [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024) - [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021) - [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021) - [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022) - [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017) - [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024) - [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016) - [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024) - [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015) - [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020) - [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022) - [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018) - [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020) - [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018) - [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021) - [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019) - [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024) - [Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models](https://mlsanity.com/paper/2207.14626/) (2022) - [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023) - [DesnowNet: Context-Aware Deep Network for Snow Removal](https://mlsanity.com/paper/1708.04512/) (2017) - [Image Restoration with Mean-Reverting Stochastic Differential Equations](https://mlsanity.com/paper/2301.11699/) (2023) - [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022) - [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024) - [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024) - [VmambaIR: Visual State Space Model for Image Restoration](https://mlsanity.com/paper/2403.11423/) (2024) - [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021) ## Built on by (most cited first, 4 of 4) - [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026) - [MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention](https://mlsanity.com/paper/2603.01361/) (2026) - [Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling](https://mlsanity.com/paper/2605.31048/) (2026) - [Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception](https://mlsanity.com/paper/2508.19638/) (2025) ## Abstract (arXiv) Image restoration~(IR), as a fundamental multimedia data processing task, has a significant impact on downstream visual applications. In recent years, researchers have focused on developing general-purpose IR models capable of handling diverse degradation types, thereby reducing the cost and complexity of model development. Current mainstream approaches are based on three architectural paradigms: CNNs, Transformers, and Mambas. CNNs excel in efficient inference, whereas Transformers and Mamba excel at capturing long-range dependencies and modeling global contexts. While each architecture has demonstrated success in specialized, single-task settings, limited efforts have been made to effectively integrate heterogeneous architectures to jointly address diverse IR challenges. To bridge this gap, we propose RestorMixer, an efficient and general-purpose IR model based on mixed-architecture fusion. RestorMixer adopts a three-stage encoder-decoder structure, where each stage is tailored to the resolution and feature characteristics of the input. In the initial high-resolution stage, CNN-based blocks are employed to rapidly extract shallow local features. In the subsequent stages, we integrate a refined multi-directional scanning Mamba module with a multi-scale window-based self-attention mechanism. This hierarchical and adaptive design enables the model to leverage the strengths of CNNs in local feature extraction, Mamba in global context modeling, and attention mechanisms in dynamic feature refinement. Extensive experimental results demonstrate that RestorMixer achieves leading performance across multiple IR tasks while maintaining high inference efficiency. The official code can be accessed at https://github.com/ClimBin/RestorMixer.