# Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D--2D Registration for Liver Laparoscopy

arXiv: https://arxiv.org/abs/2607.17810 · HTML: https://mlsanity.com/paper/2607.17810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [Dynamic Point Fields](https://mlsanity.com/paper/2304.02626/) (2023)
- [An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion](https://mlsanity.com/paper/2401.15753/) (2024)
- [Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis](https://mlsanity.com/paper/2406.18817/) (2024)
- [Landmark-Free Preoperative-to-Intraoperative Registration in Laparoscopic Liver Resection](https://mlsanity.com/paper/2504.15152/) (2025)

## Abstract (arXiv)

Accurate 3D--2D liver registration, which aligns preoperative 3D models to partial, view-dependent intraoperative surface observations, is critical for AR-guided laparoscopic surgery but remains challenging due to severe occlusion, limited visibility, and the lack of 3D ground-truth supervision. Existing landmark-free approaches perform partial-to-complete geometric alignment, yet robust self-supervision under extreme partial visibility remains difficult. We propose Vis2Reg, a visibility-aware registration framework that explicitly constrains deformation using mask-consistent visible regions. We introduce a visibility-aware self-supervision that derives a visible-domain 3D supervision signal from intraoperative masks, enabled by differentiable point rasterization and mask-guided back-projection. This formulation improves robustness under severe occlusion while maintaining fully self-supervised learning. Vis2Reg combines a robust geometric rigid initialization module with an implicit neural deformation field for stable alignment. Vis2Reg achieves a Dice score of 92.6% and a Chamfer Distance of 1.43 mm on real intraoperative datasets, with 111 ms per-frame inference time, demonstrating both accuracy and practical efficiency.