Parameterize Structure with Differentiable Template for 3D Shape Generation

TL;DR

This paper introduces a novel method for 3D shape generation that uses a differentiable template with fixed parameters to efficiently reconstruct and generate detailed, editable shapes with part semantics, outperforming previous complex models.

Contribution

The paper proposes a parameterized, differentiable template approach for 3D shape generation that simplifies learning and improves detail reconstruction compared to prior hierarchical methods.

Findings

Effective shape reconstruction from point clouds

High-quality shape generation and interpolation

Superior performance demonstrated through extensive evaluations

Abstract

Structural representation is crucial for reconstructing and generating editable 3D shapes with part semantics. Recent 3D shape generation works employ complicated networks and structure definitions relying on hierarchical annotations and pay less attention to the details inside parts. In this paper, we propose the method that parameterizes the shared structure in the same category using a differentiable template and corresponding fixed-length parameters. Specific parameters are fed into the template to calculate cuboids that indicate a concrete shape. We utilize the boundaries of three-view drawings of each cuboid to further describe the inside details. Shapes are represented with the parameters and three-view details inside cuboids, from which the SDF can be calculated to recover the object. Benefiting from our fixed-length parameters and three-view details, our networks for reconstruction and generation are simple and effective to learn the latent space. Our method can reconstruct or generate diverse shapes with complicated details, and interpolate them smoothly. Extensive evaluations demonstrate the superiority of our method on reconstruction from point cloud, generation, and interpolation.