Abstract
We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents them as neural fields. The concept of neural fields has previously been combined with a global latent vector, a regular grid of latent vectors, or an irregular grid of latent vectors. Our new representation encodes neural fields on top of a set of vectors. We draw from multiple concepts, such as the radial basis function representation and the cross attention and self-attention function, to design a learnable representation that is especially suitable for processing with transformers. Our results show improved performance in 3D shape encoding and 3D shape generative modeling tasks. We demonstrate a wide variety of generative applications: unconditioned generation, category-conditioned generation, text-conditioned generation, point-cloud completion, and image-conditioned generation.
Abstract (translated)
我们介绍了3DShape2VecSet,这是一种为生成扩散模型设计的神经网络 fields 的新型形状表示。该形状表示可以编码以表面模型或点云为代表的3D形状,并将它们表示为神经网络 fields。神经网络 fields 的概念以前曾与一个全局隐向量、一个 regular grid 或一个不规则 grid 一起结合,我们的新表示在一组向量上编码了神经网络 fields。我们借鉴了多个概念,如径向基函数表示和交叉和自注意力函数,设计了一种适合与Transformers 进行处理的学习表示。我们的结果表明,在3D形状编码和3D形状生成建模任务中表现提高了。我们展示了多种生成应用:无条件生成、类别条件生成、文本条件生成、点云完成和图像条件生成。
URL
https://arxiv.org/abs/2301.11445
