高效生成保持视角一致的高保真3D矢量图形
ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis
- 利用3D先验与几何提取算法生成结构化矢量图
- 相比以往方法速度更快，且视图一致性显著提升
- 适合需要快速高质量3D草图的设计与交互场景
3D矢量图形在3D形状检索、概念设计和虚拟现实交互等应用中至关重要，因其能以极小表示捕捉核心结构信息。尽管近期方法在生成3D矢量图形方面展现出潜力，但普遍存在处理时间长、难以保持视角一致的问题。为此，我们提出ViewCraft3D（VC3D），一种利用3D先验高效生成3D矢量图形的方法。具体而言，该方法首先进行3D对象分析，采用几何提取算法将3D矢量图形拟合到底层结构，并通过视图一致性优化过程提升视觉质量。全面实验表明，VC3D在定性和定量评估中均优于先前方法，同时显著降低计算开销。生成的3D草图保持了良好的视图一致性，有效捕捉原物体的核心特征。
原文摘要 · Abstract (English)
3D vector graphics play a crucial role in various applications including 3D shape retrieval, conceptual design, and virtual reality interactions due to their ability to capture essential structural information with minimal representation. While recent approaches have shown promise in generating 3D vector graphics, they often suffer from lengthy processing times and struggle to maintain view consistency. To address these limitations, we propose ViewCraft3D (VC3D), an efficient method that leverages 3D priors to generate 3D vector graphics. Specifically, our approach begins with 3D object analysis, employs a geometric extraction algorithm to fit 3D vector graphics to the underlying structure, and applies view-consistent refinement process to enhance visual quality. Our comprehensive experiments demonstrate that VC3D outperforms previous methods in both qualitative and quantitative evaluations, while significantly reducing computational overhead. The resulting 3D sketches maintain view consistency and effectively capture the essential characteristics of the original objects.
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。