mlsanityData to 7 Oct 2026

Equivariant Filters for Efficient Tracking in 3D Imaging

arXiv 2103.10255 ↗First posted 18 Mar 2021cs.CV cs.LG q-bio.QMcited by 17

Not on the map. Why?

Abstract (arXiv)

We demonstrate an object tracking method for 3D images with fixed computational cost and state-of-the-art performance. Previous methods predicted transformation parameters from convolutional layers. We instead propose an architecture that does not include either flattening of convolutional features or fully connected layers, but instead relies on equivariant filters to preserve transformations between inputs and outputs (e.g. rot./trans. of inputs rotate/translate outputs). The transformation is then derived in closed form from the outputs of the filters. This method is useful for applications requiring low latency, such as real-time tracking. We demonstrate our model on synthetically augmented adult brain MRI, as well as fetal brain MRI, which is the intended use-case.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 9 of its 22 references that are in the map. First posted on arXiv 18 Mar 2021.

Builds on

9 of 22 references.

References · 9

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  3. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  4. 2018A Deep Learning Framework for Unsupervised Affine and Deformable Image Registrationcited by 160
  5. 2018TVM: An Automated End-to-End Optimizing Compiler for Deep Learningcited by 62
  6. 2018Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registrationcited by 40
  7. 2020Finding Symmetry Breaking Order Parameters with Euclidean Neural Networkscited by 30
  8. 2017Slice-to-volume medical image registration: a surveycited by 21
  9. 2018AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networkscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 7; 2025: 4; 2026: 1.

17 papers.

Sort:

  1. 2023A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypointscited by 25
  2. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  3. 2023Anatomy-aware and acquisition-agnostic joint registration with SynthMorphcited by 19
  4. 2023SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRIcited by 10
  5. 2024Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registrationcited by 5
  6. 2024Equivariant Neural Tangent Kernelscited by 4
  7. 2024Rigid Single-Slice-in-Volume registration via rotation-equivariant 2D/3D feature matchingcited by 4
  8. 2025Learning accurate rigid registration for longitudinal brain MRI from synthetic datacited by 4
  9. 2024SpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Trackingcited by 2
  10. 2024Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registrationcited by 1
  11. 2024CARL: A Framework for Equivariant Image Registrationcited by 1
  12. 2025Spatial regularisation for improved accuracy and interpretability in keypoint-based registrationcited by 1
5 more
  1. 2025Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimizationcited by 1
  2. 2022Registering Image Volumes using 3D SIFT and Discrete SP-Symmetrycited by 0
  3. 2024A Unified Deep Learning Framework for Motion Correction in Medical Imagingcited by 0
  4. 2025Equivariant symmetry-aware head pose estimation for fetal MRIcited by 0
  5. 2026Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registrationcited by 0