mlsanityData to 7 Oct 2026

Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration

arXiv 2407.19274 ↗First posted 27 Jul 2024cs.CV eess.IVcited by 9

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

Our findings indicate that adopting "advanced" computational elements fails to significantly improve registration accuracy. Instead, well-established registration-specific designs offer fair improvements, enhancing results by a marginal 1.5% over the baseline. Our findings emphasize the importance of rigorous, unbiased evaluation and contribution disentanglement of all low- and high-level registration components, rather than simply following the computer vision trends with "more advanced" computational blocks. We advocate for simpler yet effective solutions and novel evaluation metrics that go beyond conventional registration accuracy, warranting further research across diverse organs and modalities. The code is available at urlhttps://github.com/BailiangJ/rethink-reg.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 23 of its 40 references that are in the map. First posted on arXiv 27 Jul 2024.

Builds on

23 of 40 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  8. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  9. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  10. 2021Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learningcited by 125
  11. 2019Recursive Cascaded Networks for Unsupervised Medical Image Registrationcited by 105
  12. 2019Dual-Stream Pyramid Registration Networkcited by 52
11 more
  1. 2022XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attentioncited by 46
  2. 2022U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?cited by 40
  3. 2024Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registrationcited by 37
  4. 2022On Finite Difference Jacobian Computation in Deformable Image Registrationcited by 22
  5. 2023Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registrationcited by 21
  6. 2022Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learningcited by 20
  7. 2022Learning-based and unrolled motion-compensated reconstruction for cardiac MR CINE imagingcited by 11
  8. 2021Embedding Gradient-based Optimization in Image Registration Networkscited by 10
  9. 2023Motion-compensated MR CINE reconstruction with reconstruction-driven motion estimationcited by 8
  10. 2022Weakly-supervised Biomechanically-constrained CT/MRI Registration of the Spinecited by 6
  11. 2024Attention-aware non-rigid image registration for accelerated MR imagingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 3.

9 papers.

  1. 2025Beyond the LUMIR challenge: The pathway to foundational registration modelscited by 12
  2. 2025Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategiescited by 4
  3. 2025TimeFlow: Temporal Conditioning for Longitudinal Brain MRI Registration and Aging Analysiscited by 3
  4. 2024Unsupervised learning of spatially varying regularization for diffeomorphic image registrationcited by 2
  5. 2025The LUMirage: An independent evaluation of zero-shot performance in the LUMIR challengecited by 2
  6. 2025A Scalable Distributed Framework for Multimodal GigaVoxel Image Registrationcited by 0
  7. 2026Zero-shot Multi-Contrast Brain MRI Registration by Intensity Randomizing T1-weighted MRI (LUMIR25)cited by 0
  8. 2026The Right Prior for the Right Deformation: Rethinking Continuous Deformable Image Registrationcited by 0
  9. 2026Is Deformable Image Registration Ready for Brain Metastasis Reirradiation Dose Accumulation? A Longitudinal MRI Benchmark of Registration Accuracycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Mamba-R: Vision Mamba ALSO Needs Registers
  2. 2024MambaReg: Mamba-Based Disentangled Convolutional Sparse Coding for Unsupervised Deformable Multi-Modal Image Registration
  3. 2024MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration
  4. 2026Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation
  5. 2026Registers Matter for Pixel-Space Diffusion Transformers
  6. 2024Autoregressive Pretraining with Mamba in Vision
  7. 2025EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
  8. 2026Beyond ZOH: Advanced Discretization Strategies for Vision Mamba