用512维谱特征代替复杂网格，高效生成高质量3D形状
A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generation
- 通过奇异值分解将高维网格压缩为512维谱特征向量
- 仅用512个数编码1.5万顶点网格，无需训练即可重建
- 适合数据少或显存有限场景，生成质量媲美顶尖方法
近期基于高维形状隐式表示的学习方法在3D生成任务中取得显著进展。传统方法依赖训练好的自编码器获取连续隐式表示，计算成本较高。本文提出一种新框架SpoDify，利用奇异值分解（SVD）进行形状编码，将得到的特征向量存储用于后续解码，而生成建模在特征空间中完成。该方法能高效地将复杂网格编码为连续隐式表示，例如将15,000顶点的网格压缩为512维隐码，且无需学习过程。在样本有限或GPU资源受限的场景下表现优异，在网格生成任务中可生成与当前最优方法相当的高质量形状。
原文摘要 · Abstract (English)
Recent advancements in learning latent codes derived from high-dimensional shapes have demonstrated impressive outcomes in 3D generative modeling. Traditionally, these approaches employ a trained autoencoder to acquire a continuous implicit representation of source shapes, which can be computationally expensive. This paper introduces a novel framework, spectral-domain diffusion for high-quality shape generation SpoDify, that utilizes singular value decomposition (SVD) for shape encoding. The resulting eigenvectors can be stored for subsequent decoding, while generative modeling is performed on the eigenfeatures. This approach efficiently encodes complex meshes into continuous implicit representations, such as encoding a 15k-vertex mesh to a 512-dimensional latent code without learning. Our method exhibits significant advantages in scenarios with limited samples or GPU resources. In mesh generation tasks, our approach produces high-quality shapes that are comparable to state-of-the-art methods.
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。