PaNDaS: Learnable Deformation Modeling with Localized Control
This addresses challenges in 3D modeling for applications like animation or medical imaging by allowing versatile partial deformations without optimization at inference.
The paper tackles the problem of partial non-rigid shape deformations by learning deformations at the point level, enabling localized control of 3D surface meshes with state-of-the-art accuracy and greater locality for shape reconstruction and interpolation.
Non-rigid shape deformations pose significant challenges, and most existing methods struggle to handle partial deformations effectively. We propose to learn deformations at the point level, which allows for localized control of 3D surface meshes, enabling Partial Non-rigid Deformations and interpolations of Surfaces (PaNDaS). Unlike previous approaches, our method can restrict the deformations to specific parts of the shape in a versatile way. Moreover, one can mix and combine various poses from the database, all while not requiring any optimization at inference time. We demonstrate state-of-the-art accuracy and greater locality for shape reconstruction and interpolation compared to approaches relying on global shape representation across various types of human surface data. We also demonstrate several localized shape manipulation tasks and show that our method can generate new shapes by combining different input deformations. Code and data will be made available after the reviewing process.