# A denoised Mean Teacher for domain adaptive point cloud registration

arXiv: https://arxiv.org/abs/2306.14749 · HTML: https://mlsanity.com/paper/2306.14749/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 21 of 21)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration](https://mlsanity.com/paper/1809.06130/) (2018)
- [Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks](https://mlsanity.com/paper/2006.16148/) (2020)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)
- [Recursive Cascaded Networks for Unsupervised Medical Image Registration](https://mlsanity.com/paper/1907.12353/) (2019)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [Deep Learning in Medical Image Registration: A Review](https://mlsanity.com/paper/1912.12318/) (2019)
- [Unsupervised domain adaptation for medical imaging segmentation with self-ensembling](https://mlsanity.com/paper/1811.06042/) (2018)
- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds](https://mlsanity.com/paper/2203.16895/) (2022)
- [Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration](https://mlsanity.com/paper/1807.00467/) (2018)
- [Deep learning based geometric registration for medical images: How accurate can we get without visual features?](https://mlsanity.com/paper/2103.00885/) (2021)
- [Double-Uncertainty Guided Spatial and Temporal Consistency Regularization Weighting for Learning-based Abdominal Registration](https://mlsanity.com/paper/2107.02433/) (2021)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [Adapting the Mean Teacher for keypoint-based lung registration under geometric domain shifts](https://mlsanity.com/paper/2207.00371/) (2022)

## Built on by (most cited first, 1 of 1)

- [PointVoxelFormer -- Reviving point cloud networks for 3D medical imaging](https://mlsanity.com/paper/2412.17390/) (2024)

## Abstract (arXiv)

Point cloud-based medical registration promises increased computational efficiency, robustness to intensity shifts, and anonymity preservation but is limited by the inefficacy of unsupervised learning with similarity metrics. Supervised training on synthetic deformations is an alternative but, in turn, suffers from the domain gap to the real domain. In this work, we aim to tackle this gap through domain adaptation. Self-training with the Mean Teacher is an established approach to this problem but is impaired by the inherent noise of the pseudo labels from the teacher. As a remedy, we present a denoised teacher-student paradigm for point cloud registration, comprising two complementary denoising strategies. First, we propose to filter pseudo labels based on the Chamfer distances of teacher and student registrations, thus preventing detrimental supervision by the teacher. Second, we make the teacher dynamically synthesize novel training pairs with noise-free labels by warping its moving inputs with the predicted deformations. Evaluation is performed for inhale-to-exhale registration of lung vessel trees on the public PVT dataset under two domain shifts. Our method surpasses the baseline Mean Teacher by 13.5/62.8%, consistently outperforms diverse competitors, and sets a new state-of-the-art accuracy (TRE=2.31mm). Code is available at https://github.com/multimodallearning/denoised_mt_pcd_reg.