Test Time Adaptation Methods for Point Cloud Registration in Laparoscopic Surgery
Quick Answer
This study presents modified test-time adaptation (TTA) methods for 3D point cloud registration in laparoscopic surgery, addressing challenges like asymmetric shifts and noise.
Quick Take
By evaluating four approaches, the research finds that input adaptation offers the best performance with low inference latency, improving registration accuracy on corrupted synthetic and real data across datasets.
Key Points
- Modified TTA methods enhance 3D point cloud registration for laparoscopic surgery.
- Input adaptation shows consistent error reductions across datasets with low inference latency.
- Four approaches evaluated include auxiliary-task model updates and feature alignment.
- Normalization adaptation degrades performance on P2ILReg benchmark.
- Eight types of corruption tested on synthetic targets at five severity levels.
Paper Resources
📖 Reader Mode
~2 min readAbstract:3D point cloud registration in laparoscopic surgery estimates the transformation between an intraoperative organ reconstructed from video and its preoperative mesh. Because ground-truth transformations are unavailable for real data, supervised networks are trained on synthetic organ pairs. At test time, real reconstructions differ from synthetic data and are noisy, sparse, and occluded, which degrades correspondence estimation. Test-time adaptation (TTA) can reduce this domain shift, but existing methods mainly rely on logits, entropy, class prototypes, or cache memories unavailable in registration. Registration also involves paired inputs with an asymmetric shift that primarily affects the intraoperative cloud. We analyse and modify state-of-the-art TTA methods from three families to 3D registration: model, normalization, and input adaptation. We analyze four representative approaches based on auxiliary-task model updates, backpropagation-free token purging, feature alignment, and layer-normalization calibration. We modify them to handle asymmetric shifts between preoperative and intraoperative point clouds and replace classification-based entropy objectives. Using a correspondence-based model trained on clean synthetic source data, we evaluate adaptation to corrupted synthetic and real target data on P2P and P2ILReg. For synthetic targets, we apply eight corruptions, including uniform noise and global density reduction, at five severity levels. All methods improve registration on P2P, whereas normalization adaptation degrades performance on P2ILReg. Considering the computational overhead of backpropagation-based adaptation, input adaptation is the most promising option for laparoscopic surgery, providing low inference latency and consistent error reductions across datasets. Code: this https URL
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2608.02883 [cs.CV] |
| (or arXiv:2608.02883v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02883 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nina Bodelot [view email]
[v1]
Mon, 3 Aug 2026 21:11:13 UTC (452 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.