SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion
Paper
β’
2412.10437
β’
Published
β’
2
SVG Differentiable Rendering Group
community
AI & ML interests
SVG Differentiable Rendering: Generating vector graphics using neural networks.
Recent Activity
View all activity
SVGRender's activity
hjc-owoΒ
authored
a
paper
10 days ago
xingxmΒ
updated
a
Space
10 months ago
Post
1487
π New Research Alert - CVPR 2024! π
π Title: "SVGDreamer: Text-Guided SVG Generation with Diffusion Model"
π TL;DR: Given a text prompt, SVGDreamer can generate editable and versatile high-fidelity vector graphics.
π Description: In this work, the author has introduced SVGDreamer, an innovative model for text-guided vector graphics synthesis. SVGDreamer incorporates two crucial technical designs: semantic-driven image vectorization (SIVE) and vectorized particle-based score distillation (VPSD), which empower our model to generate vector graphics with high editability, superior visual quality, and notable diversity.
π₯ Authors: [Ximing Xing](https://ximinng.github.io/), Haitao Zhou, Chuang Wang, [Jing zhang](https://hellojing89.github.io/), [Dong Xu](https://www.cs.hku.hk/index.php/people/academic-staff/dongxu), and [Qian Yu](https://yuqian1023.github.io/)
π Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA πΊπΈ
π Keywords: #SVGDreamer #Text-to-SVG #SVG #Diffusion #CVPR2024
Resources:
π arXiv Paper: https://arxiv.org/abs/2312.16476
π Github Page: https://ximinng.github.io/SVGDreamer-project/
π Code Repository: https://github.com/ximinng/SVGDreamer
π Blog: https://huggingface.co/blog/xingxm/svgdreamer
π Title: "SVGDreamer: Text-Guided SVG Generation with Diffusion Model"
π TL;DR: Given a text prompt, SVGDreamer can generate editable and versatile high-fidelity vector graphics.
π Description: In this work, the author has introduced SVGDreamer, an innovative model for text-guided vector graphics synthesis. SVGDreamer incorporates two crucial technical designs: semantic-driven image vectorization (SIVE) and vectorized particle-based score distillation (VPSD), which empower our model to generate vector graphics with high editability, superior visual quality, and notable diversity.
π₯ Authors: [Ximing Xing](https://ximinng.github.io/), Haitao Zhou, Chuang Wang, [Jing zhang](https://hellojing89.github.io/), [Dong Xu](https://www.cs.hku.hk/index.php/people/academic-staff/dongxu), and [Qian Yu](https://yuqian1023.github.io/)
π Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA πΊπΈ
π Keywords: #SVGDreamer #Text-to-SVG #SVG #Diffusion #CVPR2024
Resources:
π arXiv Paper: https://arxiv.org/abs/2312.16476
π Github Page: https://ximinng.github.io/SVGDreamer-project/
π Code Repository: https://github.com/ximinng/SVGDreamer
π Blog: https://huggingface.co/blog/xingxm/svgdreamer