mlsanityData to 7 Oct 2026

MambaIC: State Space Models for High-Performance Learned Image Compression

arXiv 2503.12461 ↗First posted 16 Mar 2025cs.CV eess.IVcited by 18

Not on the map. Why?

Abstract (arXiv)

A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose significant bottlenecks, limiting practical applications. Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods and improve image compression from multiple perspectives. In this paper, we integrate the advantages of SSMs for better efficiency-performance trade-off and propose an enhanced image compression approach through refined context modeling, which we term MambaIC. Specifically, we explore context modeling to adaptively refine the representation of hidden states. Additionally, we introduce window-based local attention into channel-spatial entropy modeling to reduce potential spatial redundancy during compression, thereby increasing efficiency. Comprehensive qualitative and quantitative results validate the effectiveness and efficiency of our approach, particularly for high-resolution image compression. Code is released at https://github.com/AuroraZengfh/MambaIC.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

36 of 49 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  7. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  8. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  9. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  10. 2024VMamba: Visual State Space Modelcited by 955
  11. 2018Variational image compression with a scale hyperpriorcited by 910
  12. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
24 more
  1. 2022Simplified State Space Layers for Sequence Modelingcited by 776
  2. 2016End-to-end Optimized Image Compressioncited by 673
  3. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  4. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  5. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  6. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 495
  7. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
  8. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  9. 2022Long Range Language Modeling via Gated State Spacescited by 265
  10. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  11. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 235
  12. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 222
  13. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  14. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  15. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  16. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  17. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  18. 2021Transformer-based Image Compressioncited by 60
  19. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  20. 2023PPT: Token Pruning and Pooling for Efficient Vision Transformerscited by 37
  21. 2024MambaVC: Learned Visual Compression with Selective State Spacescited by 28
  22. 2024Dimba: Transformer-Mamba Diffusion Modelscited by 26
  23. 2025TR-DQ: Time-Rotation Diffusion Quantizationcited by 18
  24. 2024QMamba: On First Exploration of Vision Mamba for Image Quality Assessmentcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 10.

18 papers.

Sort:

By area:

  1. 2025Content-Aware Mamba for Learned Image Compressioncited by 5
  2. 2025Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridgecited by 4
  3. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  4. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  5. 2025Progressive Learned Image Compression for Machine Perceptioncited by 1
  6. 2026Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidencecited by 1
  7. 2026Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compressioncited by 1
  8. 2026Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compressioncited by 1
  9. 2025FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priorscited by 0
  10. 2025ReactionMamba: Generating Short & Long Human Reaction Sequencescited by 0
  11. 2025Joint Multi-scale Gated Transformer and Prior-guided Convolutional Network for Learned Image Compressioncited by 0
  12. 2025Benchmarking and Enhancing VLM for Compressed Image Understandingcited by 0
6 more
  1. 2026Understanding Rate-Distortion Performance in Distributed Transformer Inferencecited by 0
  2. 2026HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compressioncited by 0
  3. 2026Adaptive Learned Image Compression with Graph Neural Networkscited by 0
  4. 2026What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapterscited by 0
  5. 2026MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstructioncited by 0
  6. 2026Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Codingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression
  2. 2025CMamba: Learned Image Compression with State Space Models
  3. 2023Multistage Spatial Context Models for Learned Image Compression
  4. 2024Efficient Image Compression Using Advanced State Space Models
  5. 2026Geometric Transformation-Embedded Mamba for Learned Video Compression
  6. 2024StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos
  7. 2025Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
  8. 2025State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models