Learning quadrangulated patches for 3D shape parameterization and completion

TL;DR

This paper introduces a new 3D shape parameterization method using surface patches oriented by mesh quadrangulation, enabling effective shape completion, inpainting, and compression through learned patch dictionaries.

Contribution

It presents a novel patch-based shape parameterization and dictionary learning approach that handles variable patch sizes and improves 3D shape reconstruction and completion.

Findings

Effective shape inpainting and hole filling demonstrated.

Successful 3D mesh reconstruction from patch encoding.

Applicable to both synthetic and real-world 3D scans.

Abstract

We propose a novel 3D shape parameterization by surface patches, that are oriented by 3D mesh quadrangulation of the shape. By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape. Unlike previous methods, we are able to encode surface patches of variable size as determined by the user. We propose novel methods for dictionary learning and patch reconstruction based on the query of a noisy input patch with holes. We evaluate the patch dictionary towards various applications in 3D shape inpainting, denoising and compression. Our method is able to predict missing vertices and inpaint moderately sized holes. We demonstrate a complete pipeline for reconstructing the 3D mesh from the patch encoding. We validate our shape parameterization and reconstruction methods on both synthetic shapes and real world scans. We show that our patch dictionary performs successful shape completion of complicated surface textures.