Cloud Sphere: A 3D Shape Representation via Progressive Deformation

TL;DR

This paper introduces a novel 3D shape representation method called Cloud Sphere, which uses progressive deformation of a spherical point cloud to capture shape features and facilitate shape reconstruction and correspondence.

Contribution

It proposes a new shape representation via progressive deformation and a PDAE model to learn stage-aware descriptions for high-fidelity 3D shape reconstruction.

Findings

High-fidelity shape reconstruction achieved

Topology preservation in multi-stage deformation

Effective shape correspondence derivation

Abstract

In the area of 3D shape analysis, the geometric properties of a shape have long been studied. Instead of directly extracting representative features using expert-designed descriptors or end-to-end deep neural networks, this paper is dedicated to discovering distinctive information from the shape formation process. Concretely, a spherical point cloud served as the template is progressively deformed to fit the target shape in a coarse-to-fine manner. During the shape formation process, several checkpoints are inserted to facilitate recording and investigating the intermediate stages. For each stage, the offset field is evaluated as a stage-aware description. The summation of the offsets throughout the shape formation process can completely define the target shape in terms of geometry. In this perspective, one can derive the point-wise shape correspondence from the template inexpensively, which benefits various graphic applications. In this paper, the Progressive Deformation-based Auto-Encoder (PDAE) is proposed to learn the stage-aware description through a coarse-to-fine shape fitting task. Experimental results show that the proposed PDAE has the ability to reconstruct 3D shapes with high fidelity, and consistent topology is preserved in the multi-stage deformation process. Additional applications based on the stage-aware description are performed, demonstrating its universality.