Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yidi, Xiao, Jun, Lu, Zhengda, Wang, Yiqun, Jiang, Haiyong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916761986662400
author Li, Yidi
Xiao, Jun
Lu, Zhengda
Wang, Yiqun
Jiang, Haiyong
author_facet Li, Yidi
Xiao, Jun
Lu, Zhengda
Wang, Yiqun
Jiang, Haiyong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility
Li, Yidi
Xiao, Jun
Lu, Zhengda
Wang, Yiqun
Jiang, Haiyong
Computer Vision and Pattern Recognition
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.
title Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.21377