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 2502.02187cs.CVcs.AI
收藏

ShapeShifter:使用多尺度和稀疏点-体素扩散的3D变体生成

ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion

Inria(法国国家信息与自动化研究所);Adobe Research(奥多比研究院);IP Paris(巴黎综合理工学院)

Nissim Maruani, Wang Yifan, Matthew Fisher, Pierre Alliez, Mathieu Desbrun

AI总结:

提出ShapeShifter模型,利用稀疏体素网格与点、法线、颜色采样的多尺度架构,从单个参考模型高效生成保留细节、适用多种表面的3D形状变体,并支持交互式控制。

摘要:

本文提出了ShapeShifter,这是一种新型3D生成模型,能够学习基于单个参考模型合成形状变体。尽管3D物体的生成方法最近受到广泛关注,但现有技术通常缺乏几何细节,并且/或者需要漫长的训练时间和大量资源。我们的方法通过在多尺度神经架构中结合稀疏体素网格以及点、法线和颜色采样来解决这些问题,该架构能够高效且并行地进行训练。我们表明,所得变体能够更好地捕捉原始输入的精细细节,并且相比以往基于SDF的方法,能够处理更通用的表面类型。此外,我们提供了3D形状变体的交互式生成,在需要时允许在设计循环中加入更多人工控制。

英文摘要:

This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and point, normal, and color sampling within a multiscale neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can handle more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed.

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。

↑