让矢量图支持任意视角观看和动态显隐，生成更真实复杂的图形。
Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility
- 双分支优化框架，融合3D高斯点云与矢量图生成
- 通过渐进式引导实现粗到细的细节控制，提升跨视角一致性
- 新增可视性感知渲染模块，自动处理遮挡关系，适合复杂矢量设计
本文提出一种新型文本到矢量图形生成方法 Dream3DVG，支持任意视角观看、渐进式细节优化及视点依赖的遮挡感知。该方法采用双分支优化框架，包含辅助的3D Gaussian Splatting（3DGS）优化分支与3D矢量图形优化分支。3DGS分支有效弥合文本提示与矢量图形之间的领域差距，提供更一致的引导；同时通过调度无分类器引导，实现从初始粗略形状到后期精细细节的渐进式控制。此外，通过设计可视性感知渲染模块，提升了视点依赖遮挡处理能力。在3D草图与3D图标数据集上的大量实验表明，该方法在不同抽象层级的细节表现、跨视角一致性以及遮挡感知笔画裁剪方面均优于现有方法。
原文摘要 · Abstract (English)
This work presents a novel text-to-vector graphics generation approach, Dream3DVG, allowing for arbitrary viewpoint viewing, progressive detail optimization, and view-dependent occlusion awareness. Our approach is a dual-branch optimization framework, consisting of an auxiliary 3D Gaussian Splatting optimization branch and a 3D vector graphics optimization branch. The introduced 3DGS branch can bridge the domain gaps between text prompts and vector graphics with more consistent guidance. Moreover, 3DGS allows for progressive detail control by scheduling classifier-free guidance, facilitating guiding vector graphics with coarse shapes at the initial stages and finer details at later stages. We also improve the view-dependent occlusions by devising a visibility-awareness rendering module. Extensive results on 3D sketches and 3D iconographies, demonstrate the superiority of the method on different abstraction levels of details, cross-view consistency, and occlusion-aware stroke culling.
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。