MedGS extends Gaussian Splatting with a relightable model tailored to endoscopic imaging where light and camera are co-located, achieving better novel-view synthesis and tissue editing than baselines.
Neural-pull: Learning signed distance functions from point clouds by learning to pull space onto surfaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2representative citing papers
citing papers explorer
-
MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging
MedGS extends Gaussian Splatting with a relightable model tailored to endoscopic imaging where light and camera are co-located, achieving better novel-view synthesis and tissue editing than baselines.
- NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration