G2CNN: Geometric Prior Based GCNN for Single-View 3D Reconstruction with Loop Subdivision

Abstract

Single-view 3D reconstruction is a fundamental operation in computer vision. Although significant progress has been made by learning-based approaches, it remains a challenge that the reconstructed mesh is usually coarse since the geometric prior is ignored. In this paper, we propose a geometric prior based graph convolution neural network model (named G<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>CNN) for single-view 3D reconstruction with Loop subdivision. G<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>CNN is a data-driven deep neural network (DNN) with the geometry knowledge. To make the reconstructed results with abundant geometric details, we generate shapes with a coarse-to-fine strategy and utilize the Gaussian curvature loss as a geometric supervision. Furthermore, to produce the physically accurate 3D geometry, the mesh subdivision module is designed with Loop subdivision to exploit the vertex localizations and connectivity, which can refine and smooth the mesh surface. Experimental results on both synthesized data and real data demonstrate the effectiveness of our method in terms of both subjective and objective quality.