arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.13289cs.CV
收藏

文本到3D形状生成

Text-to-3D Shape Generation

Simon Fraser University(西蒙菲莎大学);Amii(Amii研究院)

Han-Hung Lee, Manolis Savva, Angel X. Chang

AI总结:

本文综述了文本到3D形状生成的底层技术与方法,根据监督数据类型对近期研究进行系统分类,并探讨了现有局限与未来方向。

摘要:

近年来,文本到3D形状生成领域的研究与兴趣呈现爆发式增长。许多进展得益于3D表示技术的进步、支持生成式AI模型的文本与图像数据的大规模预训练及表示学习,以及可微渲染。能够执行文本到3D形状生成的计算系统令大众为之着迷,因为它们使非专业用户能够直接从文本轻松创建3D内容。然而,该问题领域仍存在诸多局限与挑战。在本份最新技术报告中,我们调研了支持文本到3D形状生成的底层技术与方法,以总结背景文献。随后,我们根据所需监督数据的类型,对近期关于文本到3D形状生成的研究进行了系统分类。最后,我们讨论了现有各类方法的局限性,并勾勒了未来研究的潜在方向。

英文摘要:

Recent years have seen an explosion of work and interest in text-to-3D shape generation. Much of the progress is driven by advances in 3D representations, large-scale pretraining and representation learning for text and image data enabling generative AI models, and differentiable rendering. Computational systems that can perform text-to-3D shape generation have captivated the popular imagination as they enable non-expert users to easily create 3D content directly from text. However, there are still many limitations and challenges remaining in this problem space. In this state-of-the-art report, we provide a survey of the underlying technology and methods enabling text-to-3D shape generation to summarize the background literature. We then derive a systematic categorization of recent work on text-to-3D shape generation based on the type of supervision data required. Finally, we discuss limitations of the existing categories of methods, and delineate promising directions for future work.

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。

↑