SPLICE:从局部语义提取到全局神经混合的部件级3D形状编辑
SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing
AI总结:
SPLICE通过部件级神经隐式表示实现直观且高保真的3D形状编辑,支持多种编辑操作并提升编辑效果。
摘要:
神经隐式表示在3D形状编辑中展现出了巨大潜力,因为它们能够建模高级语义和连续几何表示。然而,现有方法往往存在编辑性有限、缺乏部件级控制以及在修改或重新排列形状部件时产生不自然结果的问题。在本文中,我们提出了SPLICE,一种新的部件级神经隐式表示方法,能够实现直观、结构感知和高保真的形状编辑。通过独立编码每个形状部件并使用参数化高斯椭球体定位它们,SPLICE有效地隔离了部件特定的特征,同时丢弃可能阻碍灵活操作的全局上下文。然后采用基于全局注意力的解码器来整合部件,进一步通过注意力引导的过滤机制防止信息在对称或相邻组件之间泄漏。通过这种架构,SPLICE支持各种部件级编辑操作,包括平移、旋转、缩放、删除、复制和跨形状部件混合。这些操作使用户能够灵活地探索设计变化,同时保持语义一致性和维持结构合理性。广泛的实验表明,SPLICE在多样化的形状编辑任务中在定性和定量上均优于现有方法。
英文摘要:
Neural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model high-level semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.
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。