arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.17618cs.CV
收藏

ShapeGPT:基于统一多模态语言模型的三维形状生成

ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model

Fudan University(复旦大学);Tencent(腾讯);ShanghaiTech University(上海科技大学);Zhejiang Lab(之江实验室)

Fukun Yin, Xin Chen, Chi Zhang, Biao Jiang, Zibo Zhao, Jiayuan Fan, Gang Yu, Taihao Li, Tao Chen

AI总结:

本文提出ShapeGPT,通过“词-句-段”框架将三维形状离散化并与指令文本结合,利用三阶段训练构建统一多模态语言模型,在文本到形状、形状到文本、形状补全与编辑等任务上取得可比性能。

摘要:

大型语言模型的出现,通过指令驱动的方法实现了灵活性,已经革新了许多传统的生成任务,但用于三维数据的大型模型,特别是在综合处理三维形状与其他模态方面,仍处于探索不足的状态。通过实现基于指令的形状生成,多功能的多模态生成式形状模型可以显著惠及三维虚拟构建和网络辅助设计等多个领域。在本工作中,我们提出了ShapeGPT,这是一个包含形状的多模态框架,旨在利用强大的预训练语言模型来处理多种与形状相关的任务。具体来说,ShapeGPT采用“词-句-段”框架,将连续形状离散化为形状词,进一步将这些词组装为形状句,并将形状与指令文本整合为多模态段落。为了学习这一形状-语言模型,我们采用三阶段训练方案,包括形状表示、多模态对齐和基于指令的生成,以对齐形状-语言码本并学习这些模态之间错综复杂的关联。大量实验表明,ShapeGPT在文本到形状、形状到文本、形状补全和形状编辑等形状相关任务上均取得了可比的性能。

英文摘要:

The advent of large language models, enabling flexibility through instruction-driven approaches, has revolutionized many traditional generative tasks, but large models for 3D data, particularly in comprehensively handling 3D shapes with other modalities, are still under-explored. By achieving instruction-based shape generations, versatile multimodal generative shape models can significantly benefit various fields like 3D virtual construction and network-aided design. In this work, we present ShapeGPT, a shape-included multi-modal framework to leverage strong pre-trained language models to address multiple shape-relevant tasks. Specifically, ShapeGPT employs a word-sentence-paragraph framework to discretize continuous shapes into shape words, further assembles these words for shape sentences, as well as integrates shape with instructional text for multi-modal paragraphs. To learn this shape-language model, we use a three-stage training scheme, including shape representation, multimodal alignment, and instruction-based generation, to align shape-language codebooks and learn the intricate correlations among these modalities. Extensive experiments demonstrate that ShapeGPT achieves comparable performance across shape-relevant tasks, including text-to-shape, shape-to-text, shape completion, and shape editing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑