High-fidelity 3D Model Compression based on Key Spheres

TL;DR

This paper introduces a novel 3D model compression method using neural SDFs with explicit key spheres, achieving high-fidelity reconstruction with minimal storage by leveraging key sphere-based shape representation.

Contribution

The paper proposes a new SDF prediction network that uses explicit key spheres as input, significantly improving 3D model reconstruction accuracy while maintaining high compression.

Findings

Achieves high-fidelity 3D reconstruction with minimal storage.

Outperforms previous methods on three datasets.

Significantly improves shape reconstruction accuracy.

Abstract

In recent years, neural signed distance function (SDF) has become one of the most effective representation methods for 3D models. By learning continuous SDFs in 3D space, neural networks can predict the distance from a given query space point to its closest object surface,whose positive and negative signs denote inside and outside of the object, respectively. Training a specific network for each 3D model, which individually embeds its shape, can realize compressed representation of objects by storing fewer network (and possibly latent) parameters. Consequently, reconstruction through network inference and surface recovery can be achieved. In this paper, we propose an SDF prediction network using explicit key spheres as input. Key spheres are extracted from the internal space of objects, whose centers either have relatively larger SDF values (sphere radii), or are located at essential positions. By inputting the spatial information of multiple spheres which imply different local shapes, the proposed method can significantly improve the reconstruction accuracy with a negligible storage cost. Compared to previous works, our method achieves the high-fidelity and high-compression 3D object coding and reconstruction. Experiments conducted on three datasets verify the superior performance of our method.