PaNDaS: Learnable Deformation Modeling with Localized Control

TL;DR

PaNDaS introduces a learnable, localized deformation model for 3D shapes that enables partial deformations, pose interpolation, and shape manipulation without optimization at inference, achieving state-of-the-art accuracy.

Contribution

The paper presents a novel point-level deformation learning method that allows localized control and mixing of shapes, surpassing previous global approaches.

Findings

State-of-the-art accuracy in shape reconstruction and interpolation.

Enhanced locality in shape deformation and manipulation.

Ability to generate new shapes by combining different deformations.

Abstract

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.