mlsanityData to 14 Oct 2026

Equivariant symmetry-aware head pose estimation for fetal MRI

arXiv 2512.04890 ↗First posted 4 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of diagnostic 2D MRI slices with 6-DoF head pose estimation, supported by rapid low-resolution 3D MRI volumes acquired before each 2D slice. Existing pose estimation methods struggle to generalize to clinical volumes due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, supporting future clinical translation. Our implementation is publicly available at github.com/MedicalVisionGroup/E3-Pose.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 92 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

45 of 92 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  4. 2016Group Equivariant Convolutional Networkscited by 1,165
  5. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  8. 2018Spherical CNNscited by 456
  9. 2019General E(2)-Equivariant Steerable CNNscited by 446
  10. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  11. 2016Steerable CNNscited by 305
  12. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
33 more
  1. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
  2. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
  3. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 177
  4. 2022e3nn: Euclidean Neural Networkscited by 174
  5. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  6. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 97
  7. 2020An Analysis of SVD for Deep Rotation Estimationcited by 86
  8. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  9. 2020Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Drivingcited by 73
  10. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  11. 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)cited by 42
  12. 2018Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registrationcited by 40
  13. 2019Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spacescited by 34
  14. 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
  15. 20206D Object Pose Regression via Supervised Learning on Point Cloudscited by 33
  16. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  17. 2022SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRIcited by 26
  18. 2023A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypointscited by 25
  19. 2021Implicit Bias of Linear Equivariant Networkscited by 19
  20. 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Predictioncited by 18
  21. 2021Equivariant Filters for Efficient Tracking in 3D Imagingcited by 17
  22. 2022Leveraging Equivariant Features for Absolute Pose Regressioncited by 17
  23. 2019A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical Imagingcited by 14
  24. 2023SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRIcited by 10
  25. 2020Handling Object Symmetries in CNN-based Pose Estimationcited by 8
  26. 2024Registration by Regression (RbR): a framework for interpretable and flexible atlas registrationcited by 8
  27. 2023Equivariant Single View Pose Prediction Via Induced and Restricted Representationscited by 6
  28. 2021Rapid head-pose detection for automated slice prescription of fetal-brain MRIcited by 4
  29. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  30. 2021Equivariance and generalization in neural networkscited by 3
  31. 2023Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical datacited by 2
  32. 2024SpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Trackingcited by 2
  33. 2025Robust Fetal Pose Estimation across Gestational Ages via Cross-Population Augmentationcited by 2

Built on by

Not cited yet.