# NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration

arXiv: https://arxiv.org/abs/2511.14286 · HTML: https://mlsanity.com/paper/2511.14286/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 97 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [3DRegNet: A Deep Neural Network for 3D Point Registration](https://mlsanity.com/paper/1904.01701/) (2019)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration](https://mlsanity.com/paper/1905.04153/) (2019)
- [You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors](https://mlsanity.com/paper/2109.00182/) (2021)
- [Automatic Annotation of Hip Anatomy in Fluoroscopy for Robust and Efficient 2D/3D Registration](https://mlsanity.com/paper/1911.07042/) (2019)
- [The Impact of Machine Learning on 2D/3D Registration for Image-guided Interventions: A Systematic Review and Perspective](https://mlsanity.com/paper/2108.02238/) (2021)
- [Neural Implicit Surface Reconstruction of Freehand 3D Ultrasound Volume with Geometric Constraints](https://mlsanity.com/paper/2401.05915/) (2024)
- [FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration](https://mlsanity.com/paper/2106.03479/) (2021)
- [End-to-end Ultrasound Frame to Volume Registration](https://mlsanity.com/paper/2107.06449/) (2021)
- [Automatic registration with continuous pose updates for marker-less surgical navigation in spine surgery](https://mlsanity.com/paper/2308.02917/) (2023)
- [Deep Learning-based Point Cloud Registration for Augmented Reality-guided Surgery](https://mlsanity.com/paper/2405.03314/) (2024)
- [Unsupervised Point Cloud Registration with Self-Distillation](https://mlsanity.com/paper/2409.07558/) (2024)
- [Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery](https://mlsanity.com/paper/2108.10608/) (2021)
- [AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications](https://mlsanity.com/paper/2203.05784/) (2022)
- [UltraBoneUDF: Self-supervised Bone Surface Reconstruction from Ultrasound Based on Neural Unsigned Distance Functions](https://mlsanity.com/paper/2505.17912/) (2025)

## Abstract (arXiv)

In computer- and robot-assisted orthopedic surgery (CAOS), patient-specific surgical plans derived from preoperative imaging define target locations and implant trajectories. During surgery, these plans must be accurately transferred, relying on precise cross-registration between preoperative and intraoperative data. However, substantial modality heterogeneity across imaging modalities makes this registration challenging and error-prone. Robust, automatic, and modality-agnostic bone surface registration is therefore clinically important. We propose NeuralBoneReg, a self-supervised, surface-based framework that registers bone surfaces using 3D point clouds as a modality-agnostic representation. NeuralBoneReg includes two modules: an implicit neural unsigned distance field (UDF) that learns the preoperative bone model, and an MLP-based registration module that performs global initialization and local refinement by generating transformation hypotheses to align the intraoperative point cloud with the neural UDF. Unlike SOTA supervised methods, NeuralBoneReg operates in a self-supervised manner, without requiring inter-subject training data. We evaluated NeuralBoneReg against baseline methods on two publicly available multi-modal datasets: a CT-ultrasound dataset of the fibula and tibia (UltraBones100k) and a CT-RGB-D dataset of spinal vertebrae (SpineDepth). The evaluation also includes a newly introduced CT-ultrasound dataset of cadaveric subjects containing femur and pelvis (UltraBones-Hip), which will be made publicly available. NeuralBoneReg matches or surpasses existing methods across all datasets, achieving mean RRE/RTE of 1.83deg/2.02 mm on UltraBones100k, 1.90deg/1.56 mm on UltraBones-Hip, and 3.78deg/2.80 mm on SpineDepth. These results demonstrate strong generalizability across anatomies and modalities, providing robust and accurate cross-modal alignment for CAOS.