A Transformer-based patient-specific non-rigid point cloud registration pipeline with overlap estimation and physics-based refinement outperforms generic methods on synthetic laparoscopic data.
In: Symposium on Geometry processing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MeshOn composes two input meshes realistically without intersections by using VLM-based rigid initialization, attractive geometric losses, a barrier loss, and a diffusion prior for final deformation.
citing papers explorer
-
Towards Patient-Specific Deformable Registration in Laparoscopic Surgery
A Transformer-based patient-specific non-rigid point cloud registration pipeline with overlap estimation and physics-based refinement outperforms generic methods on synthetic laparoscopic data.
-
MeshOn: Intersection-Free Mesh-to-Mesh Composition
MeshOn composes two input meshes realistically without intersections by using VLM-based rigid initialization, attractive geometric losses, a barrier loss, and a diffusion prior for final deformation.