PaNDaS is a neural deformation model that combines per-triangle local features with a global code, enabling masked partial deformations and interpolations of 3D meshes without inference-time optimization.
Computing large deformation metric mappings via geodesic flows of diffeomorphisms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
PaNDaS: Learnable Deformation Modeling with Localized Control
PaNDaS is a neural deformation model that combines per-triangle local features with a global code, enabling masked partial deformations and interpolations of 3D meshes without inference-time optimization.