论文标题
扩散-SDF：通过Voxelized扩散的文本对形状
Diffusion-SDF: Text-to-Shape via Voxelized Diffusion
论文作者
论文摘要
随着对3D虚拟建模技术的工业关注不断上升，基于指定条件（例如文本）生成新颖的3D内容已成为一个热门问题。在本文中，我们提出了一个新的生成3D建模框架，称为“扩散-SDF”，以挑战文本对形状合成。先前的方法在3D数据表示和形状生成方面都缺乏灵活性，因此未能产生符合给定文本描述的高度多样化的3D形状。为了解决这个问题，我们提出了一个SDF自动编码器以及Voxelized扩散模型，以学习和生成3D形状的Voxelized签名距离字段（SDFS）的表示。具体来说，我们设计了一种新型的UINU-NET体系结构，该体系结构将局部以本地为中心的内网络植入标准U-NET体系结构，从而可以更好地重建与补丁无关的SDF表示。我们将方法扩展到进一步的文本到形状任务，包括文本条件的形状完成和操纵。实验结果表明，与以前的方法相比，扩散-SDF同时产生更高质量和更多样化的3D形状，它们符合给定的文本描述。代码可在以下网址找到：https：//github.com/ttlmh/diffusion-sdf
With the rising industrial attention to 3D virtual modeling technology, generating novel 3D content based on specified conditions (e.g. text) has become a hot issue. In this paper, we propose a new generative 3D modeling framework called Diffusion-SDF for the challenging task of text-to-shape synthesis. Previous approaches lack flexibility in both 3D data representation and shape generation, thereby failing to generate highly diversified 3D shapes conforming to the given text descriptions. To address this, we propose a SDF autoencoder together with the Voxelized Diffusion model to learn and generate representations for voxelized signed distance fields (SDFs) of 3D shapes. Specifically, we design a novel UinU-Net architecture that implants a local-focused inner network inside the standard U-Net architecture, which enables better reconstruction of patch-independent SDF representations. We extend our approach to further text-to-shape tasks including text-conditioned shape completion and manipulation. Experimental results show that Diffusion-SDF generates both higher quality and more diversified 3D shapes that conform well to given text descriptions when compared to previous approaches. Code is available at: https://github.com/ttlmh/Diffusion-SDF
