Multi-chart Generative Surface Modeling

TL;DR

This paper presents a novel deep learning approach for 3D shape generation using a multi-chart tensor representation and GANs, enabling high-quality, diverse, and interpolatable shape synthesis for complex anatomical structures.

Contribution

It introduces a new tensor-based multi-chart representation for genus-zero 3D shapes and integrates it with GANs to improve shape generation and reconstruction quality.

Findings

Effective generation of diverse 3D shapes including human bodies and bones.

Guarantees unique shape reconstruction through scale-translation rigidity.

Demonstrates high-quality shape interpolation and exploration.

Abstract

This paper introduces a 3D shape generative model based on deep neural networks. A new image-like (i.e., tensor) data representation for genus-zero 3D shapes is devised. It is based on the observation that complicated shapes can be well represented by multiple parameterizations (charts), each focusing on a different part of the shape. The new tensor data representation is used as input to Generative Adversarial Networks for the task of 3D shape generation. The 3D shape tensor representation is based on a multi-chart structure that enjoys a shape covering property and scale-translation rigidity. Scale-translation rigidity facilitates high quality 3D shape learning and guarantees unique reconstruction. The multi-chart structure uses as input a dataset of 3D shapes (with arbitrary connectivity) and a sparse correspondence between them. The output of our algorithm is a generative model that learns the shape distribution and is able to generate novel shapes, interpolate shapes, and explore the generated shape space. The effectiveness of the method is demonstrated for the task of anatomic shape generation including human body and bone (teeth) shape generation.