Abstract
Non-rigid point cloud registration is central to soft-tissue shape analysis, but large deformations, noise, and outliers make correspondence estimation challenging. Most learning-based methods rely on local objectives such as Chamfer distance, which encourage point-wise proximity but do not constrain the global plausibility of the predicted deformation field. We address this limitation with DINE, a maximum a posteriori framework that augments distance-based registration with a learned statistical prior over displacement vector fields. DINE is applied to two registration backbones, Robust-DefReg and DefTransNet, using a two-stage strategy: a first-stage model is trained with Chamfer distance, its predicted deformation fields are used to estimate a prior, and the model is then refined with a combined distance and negative log-prior objective. We compare a full-field PCA Gaussian prior with a per-vector normalizing-flow prior. Experiments on DeformedTissue and SynBench show lower mean Chamfer distance under deformation and corruption. On DeformedTissue, DINE-PCA reduces Chamfer distance by approximately 27–69% relative to the corresponding Stage-1 backbone across deformation levels, and improves robustness by up to 66% for outliers and 83% for Gaussian noise. On SynBench, improvements are modest at the smallest deformation levels and reach approximately 59–79% from moderate to severe deformation. These results show that constraining predictions toward deformation patterns supported by the learned training distribution can improve registration robustness; direct physical or anatomical plausibility of the deformation fields is not evaluated in this study. Code: https://github.com/BeerJii/DINE-Distance-Is-Not-Enough
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/ShapeMI_035.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=vntuDO9FLw
BibTex
@InProceedings{HomSar_DINE_MICCAISAT2026,
author = { Homscheid, Sara AND Beer, Rohit AND Kinz, Marvin AND Scherl, Claudia AND Hesser, Jürgen},
title = { { DINE: Distance Is Not Enough Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registration } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17259},
month = {pending},
page = {pending}
}