用分层向量编码器实现3D模型高效压缩与生成
LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion
- 分层架构将3D模型映射到压缩向量空间，支持无序点集输入
- 训练耗时减少30%，内存降低42%，保持高精度几何还原
- 提出级联扩散框架，适用于复杂3D生成任务
本文提出一种新型分层自编码器，将3D模型映射至高度压缩的潜在空间。该架构专为大规模数据集和基于扩散的生成建模设计，不同于以往仅适用于规则图像或体素网格的方法，其直接处理无序向量集合。每一层级控制不同层次的几何细节。实验表明，该模型能忠实表示各类3D模型的高分辨率几何特征。相较于基线方法，新架构训练时间缩短30%（0.70x），内存占用降低42%（0.58x）。我们进一步探索该表示在生成建模中的应用，提出一种级联扩散框架，每阶段均基于前一阶段条件生成，将现有图像与体素网格的级联设计拓展至向量集。
原文摘要 · Abstract (English)
This paper introduces a novel hierarchical autoencoder that maps 3D models into a highly compressed latent space. The hierarchical autoencoder is specifically designed to tackle the challenges arising from large-scale datasets and generative modeling using diffusion. Different from previous approaches that only work on a regular image or volume grid, our hierarchical autoencoder operates on unordered sets of vectors. Each level of the autoencoder controls different geometric levels of detail. We show that the model can be used to represent a wide range of 3D models while faithfully representing high-resolution geometry details. The training of the new architecture takes 0.70x time and 0.58x memory compared to the baseline. We also explore how the new representation can be used for generative modeling. Specifically, we propose a cascaded diffusion framework where each stage is conditioned on the previous stage. Our design extends existing cascaded designs for image and volume grids to vector sets.
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。