Multi-chart generative surface modeling

By Heli Ben-Hamu, Haggai Maron, Itay Kezurer, Gal Avineri, Yaron Lipman. 2018

81 citations recorded by the source corpus.

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.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Learning Gradient Fields for Shape Generation (2020, neutral): “N×3 where N is predefined) [2,18,67,56,68,17,52,59], or relies on heuristic set distance functions such as Chamfer distance and Earth Mover Distance [25,65,19,12,6].”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, methodology): “ds [47,41,23] relax the compute and memory limitations of dense voxel methods to some degree and have been shown on voxel resolutions of up to 5123. Meshes. These methods use existing [43] or learned [21,4] parameterization techniques to describe 3D surfaces by morphing 2D planes. When using mesh re”
BSP-Net: Generating Compact Meshes via Binary Space Partitioning (2019, methodology): “Few deep networks can generate polygonal meshes directly, and such methods are limited to genus-zero meshes [17, 27, 44], piece-wise genus-zero [12] meshes, meshes sharing the same connectivity [11, 41], or meshes with very low number of vertices [7].”
SAL: Sign Agnostic Learning of Shapes From Raw Data (2019, methodology): “[4] apply GAN on a collection of conformal charts.”