用稀疏体素与点云生成细节丰富的3D形状变体，训练快且可交互。
ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion
- 融合稀疏体素与点、法向、颜色信息，多尺度并行训练。
- 生成形状保留原始细节，支持更复杂的表面类型。
- 支持交互式生成，适合需要人工干预的设计场景。
本文提出ShapeShifter，一种基于单个参考模型生成3D形状变体的新方法。尽管近期3D生成方法备受关注，但现有技术常缺乏几何细节，或需长时间训练与大量资源。本方法通过在多尺度神经架构中结合稀疏体素网格与点、法向、颜色采样，实现高效并行训练。结果表明，生成的变体能更好保留输入形状的精细特征，且对更广泛的曲面类型具有更强适应性，优于以往基于SDF的方法。此外，系统支持交互式生成，可在设计流程中提供更高的人机控制能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。