用神经位移场压缩3D网格，实现4到380倍的高效压缩。
Mesh Compression with Quantized Neural Displacement Fields
- 用小网络编码网格表面的位移场进行压缩。
- 在4~380倍压缩比下保持精细几何纹理。
- 适合需要高保真3D模型压缩的场景。
隐式神经表示（INRs）已成功用于压缩多种3D表面表示，如有符号距离函数（SDF）、体素网格，以及图像、视频和音频等结构化数据。然而，这些方法在处理无结构数据（如3D网格和点云）时仍受限。本文提出一种简单而有效的方法，将INRs扩展应用于3D三角网格压缩。该方法通过一个小神经网络编码一个位移场，将待压缩的粗略网格表面进行精细化重构。训练完成后，神经网络权重所占内存远低于位移场或原始表面。实验表明，该方法可在4~380倍压缩比下有效保留复杂几何纹理，并达到当前最优性能。
原文摘要 · Abstract (English)
Implicit neural representations (INRs) have been successfully used to compress a variety of 3D surface representations such as Signed Distance Functions (SDFs), voxel grids, and also other forms of structured data such as images, videos, and audio. However, these methods have been limited in their application to unstructured data such as 3D meshes and point clouds. This work presents a simple yet effective method that extends the usage of INRs to compress 3D triangle meshes. Our method encodes a displacement field that refines the coarse version of the 3D mesh surface to be compressed using a small neural network. Once trained, the neural network weights occupy much lower memory than the displacement field or the original surface. We show that our method is capable of preserving intricate geometric textures and demonstrates state-of-the-art performance for compression ratios ranging from 4x to 380x.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。