# US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recovery

arXiv: https://arxiv.org/abs/2511.15600 · HTML: https://mlsanity.com/paper/2511.15600/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 14 of 14)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [View-Guided Point Cloud Completion](https://mlsanity.com/paper/2104.05666/) (2021)
- [Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds](https://mlsanity.com/paper/2109.11453/) (2021)
- [Point-Cloud Completion with Pretrained Text-to-image Diffusion Models](https://mlsanity.com/paper/2306.10533/) (2023)
- [CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2208.00751/) (2022)
- [Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-aware Dual-Agent Framework](https://mlsanity.com/paper/2111.02167/) (2021)
- [Temporal Point Cloud Completion with Pose Disturbance](https://mlsanity.com/paper/2202.03084/) (2022)
- [Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism](https://mlsanity.com/paper/2203.10569/) (2022)
- [Robotic CBCT Meets Robotic Ultrasound](https://mlsanity.com/paper/2502.12019/) (2025)

## Built on by (most cited first, 3 of 3)

- [OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations](https://mlsanity.com/paper/2603.08279/) (2026)
- [ZODIAC: Zero-shot Octree-based Diffusion for Anatomical Completion](https://mlsanity.com/paper/2608.24422/) (2026)
- [UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound](https://mlsanity.com/paper/2609.11506/) (2026)

## Abstract (arXiv)

Ultrasound offers a radiation-free, cost-effective solution for real-time visualization of spinal landmarks, paraspinal soft tissues and neurovascular structures, making it valuable for intraoperative guidance during spinal procedures. However, ultrasound suffers from inherent limitations in visualizing complete vertebral anatomy, in particular vertebral bodies, due to acoustic shadowing effects caused by bone. In this work, we present a novel multi-modal deep learning method for completing occluded anatomical structures in 3D ultrasound by leveraging complementary information from a single X-ray image. To enable training, we generate paired training data consisting of: (1) 2D lateral vertebral views that simulate X-ray scans, and (2) 3D partial vertebrae representations that mimic the limited visibility and occlusions encountered during ultrasound spine imaging. Our method integrates morphological information from both imaging modalities and demonstrates significant improvements in vertebral reconstruction (p < 0.001) compared to state of art in 3D ultrasound vertebral completion. We perform phantom studies as an initial step to future clinical translation, and achieve a more accurate, complete volumetric lumbar spine visualization overlayed on the ultrasound scan without the need for registration with preoperative modalities such as computed tomography. This demonstrates that integrating a single X-ray projection mitigates ultrasound's key limitation while preserving its strengths as the primary imaging modality. Code and data can be found at https://github.com/miruna20/US-X-Complete