计算机科学
扩散
代表(政治)
灵活性(工程)
自编码
编码(集合论)
任务(项目管理)
实体造型
边界表示法
人工智能
理论计算机科学
边界(拓扑)
人工神经网络
程序设计语言
数学
热力学
统计
政治
政治学
物理
数学分析
经济
集合(抽象数据类型)
管理
法学
作者
Muheng Li,Yueqi Duan,Jie Zhou,Jiwen Lu
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2023-06-01
卷期号:: 12642-12651
被引量:190
标识
DOI:10.1109/cvpr52729.2023.01216
摘要
With the rising industrial attention to 3D virtual mod-eling 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 Uinll-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.
科研通智能强力驱动
Strongly Powered by AbleSci AI