Neural Progressive Meshes

TL;DR

This paper introduces a neural progressive mesh method that efficiently transmits 3D geometric data by leveraging shared local patterns and residual features, enabling progressive quality improvement over bandwidth.

Contribution

It presents a novel subdivision-based neural architecture for progressive 3D mesh compression that outperforms existing methods in quality and efficiency.

Findings

Outperforms baselines in compression ratio

Provides controllable quality via residual features

Effective on diverse complex shapes

Abstract

The recent proliferation of 3D content that can be consumed on hand-held devices necessitates efficient tools for transmitting large geometric data, e.g., 3D meshes, over the Internet. Detailed high-resolution assets can pose a challenge to storage as well as transmission bandwidth, and level-of-detail techniques are often used to transmit an asset using an appropriate bandwidth budget. It is especially desirable for these methods to transmit data progressively, improving the quality of the geometry with more data. Our key insight is that the geometric details of 3D meshes often exhibit similar local patterns even across different shapes, and thus can be effectively represented with a shared learned generative space. We learn this space using a subdivision-based encoder-decoder architecture trained in advance on a large collection of surfaces. We further observe that additional residual features can be transmitted progressively between intermediate levels of subdivision that enable the client to control the tradeoff between bandwidth cost and quality of reconstruction, providing a neural progressive mesh representation. We evaluate our method on a diverse set of complex 3D shapes and demonstrate that it outperforms baselines in terms of compression ratio and reconstruction quality.