通过分阶段变形实现文本引导下姿态一致的3D网格生成
PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation
- 分两阶段：先全局缩放，再局部细节雕刻
- 使用拉普拉斯表示与新损失函数，提升姿态保持能力
- 适合需要精确姿态控制的3D内容创作场景
三维网格变形是计算机图形学的核心任务。尽管已有多种文本引导的3D网格变形方法，但如何在遵循文本提示的同时保持原始姿态仍具挑战。本文提出PoseAlign，将变形过程分为两个阶段：全局姿态缩放和局部细节雕刻。第一阶段引入可微分的拉普拉斯表示，实现更高效平滑的全局变形；第二阶段提出一种新的姿态对齐得分蒸馏采样（pose-aligned SDS）损失，通过注意力共享机制，在保留原始姿态的前提下雕刻精细几何细节。实验表明，该方法在文本对齐度和网格质量上均表现优异，显著提升了整体变形的可控性。代码已公开于https://cousingrade6.github.io/PoseAlign。
原文摘要 · Abstract (English)
Mesh deformation, the process of altering the vertex positions of a 3D mesh while preserving its topological structure, is a cornerstone of computer graphics. Despite the recent emergence of numerous text-guided 3D mesh deformation methods, deforming an initial mesh into one that both adheres to text prompts and preserves its pose remains challenging. This paper proposes PoseAlign, which decomposes text-guided mesh deformation into two stages: global pose scaling and local detail sculpting. Specifically, in the first stage, we introduce the Laplacian as a differentiable mesh representation to enable more efficient yet smoother global deformation. Then, we propose a novel pose-aligned SDS loss by adapting score distillation sampling (SDS) with an attention-sharing mechanism, which sculptures fine-grained geometric details for the deformed mesh while preserving its original pose. PoseAlign significantly enhances the controllability of the overall deformation process, achieving a favorable balance between pose preservation and text alignment. Experiments demonstrate the competitive advantages of our method in text alignment and mesh quality. Code is available at: https://cousingrade6.github.io/PoseAlign
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。