Surface Reconstruction with Data-driven Exemplar Priors

TL;DR

This paper introduces a data-driven framework for 3D shape reconstruction from raw points by learning exemplar priors from existing models, enabling faithful and detailed reconstructions across object categories.

Contribution

It presents a novel method to learn and select exemplar shape priors from a database, improving 3D reconstruction quality over heuristic approaches.

Findings

Effective preservation of sharp features

Recovery of fine geometric details

Generalization to complex object categories

Abstract

In this paper, we propose a framework to reconstruct 3D models from raw scanned points by learning the prior knowledge of a specific class of objects. Unlike previous work that heuristically specifies particular regularities and defines parametric models, our shape priors are learned directly from existing 3D models under a framework based on affinity propagation. Given a database of 3D models within the same class of objects, we build a comprehensive library of 3D local shape priors. We then formulate the problem to select as-few-as-possible priors from the library, referred to as exemplar priors. These priors are sufficient to represent the 3D shapes of the whole class of objects from where they are generated. By manipulating these priors, we are able to reconstruct geometrically faithful models with the same class of objects from raw point clouds. Our framework can be easily generalized to reconstruct various categories of 3D objects that have more geometrically or topologically complex structures. Comprehensive experiments exhibit the power of our exemplar priors for gracefully solving several problems in 3D shape reconstruction such as preserving sharp features, recovering fine details and so on.