mlsanityData to 7 Oct 2026

Inverse Consistency by Construction for Multistep Deep Registration

arXiv 2305.00087 ↗First posted 28 Apr 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Inverse consistency is a desirable property for image registration. We propose a simple technique to make a neural registration network inverse consistent by construction, as a consequence of its structure, as long as it parameterizes its output transform by a Lie group. We extend this technique to multi-step neural registration by composing many such networks in a way that preserves inverse consistency. This multi-step approach also allows for inverse-consistent coarse to fine registration. We evaluate our technique on synthetic 2-D data and four 3-D medical image registration tasks and obtain excellent registration accuracy while assuring inverse consistency.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 10 of its 28 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

10 of 28 references.

References · 10

  1. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  2. 2020SynthMorph: learning contrast-invariant registration without acquired imagescited by 137
  3. 2020Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networkscited by 136
  4. 2020Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networkscited by 107
  5. 2019Networks for Joint Affine and Non-parametric Image Registrationcited by 44
  6. 2022textttGradICON: Approximate Diffeomorphisms via Gradient Inverse Consistencycited by 40
  7. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
  8. 2018Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registrationcited by 32
  9. 2021ICON: Learning Regular Maps Through Inverse Consistencycited by 26
  10. 2020A Multiple Decoder CNN for Inverse Consistent 3D Image Registrationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 6; 2026: 1.

12 papers.

  1. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  2. 2025Beyond the LUMIR challenge: The pathway to foundational registration modelscited by 12
  3. 2025Guiding Registration with Emergent Similarity from Pre-Trained Diffusion Modelscited by 6
  4. 2025Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategiescited by 4
  5. 2024Gaussian Primitives for Deformable Image Registrationcited by 2
  6. 2024Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairscited by 2
  7. 2024CARL: A Framework for Equivariant Image Registrationcited by 1
  8. 2024PointVoxelFormer -- Reviving point cloud networks for 3D medical imagingcited by 1
  9. 2026Reliability-Aware CT-MRI Registration: A Quality Engineering Framework with Stability Analysis and Risk Classificationcited by 1
  10. 2025Downstream Analysis of Foundational Medical Vision Models for Disease Progressioncited by 0
  11. 2025OncoReg: Medical Image Registration for Oncological Challengescited by 0
  12. 2025Biomechanical Constraints Assimilation in Deep-Learning Image Registration: Application to sliding and locally rigid deformationscited by 0