From 9ccd30e20a7b22212d493af24c822e101c5963fd Mon Sep 17 00:00:00 2001 From: Ximing Xing Date: Sun, 15 Dec 2024 22:56:38 +0800 Subject: [PATCH] fix(index): update style --- index.html | 82 ++++++++++++++++++++++++++---------------------------- 1 file changed, 39 insertions(+), 43 deletions(-) diff --git a/index.html b/index.html index 1ae747f..6fc0953 100644 --- a/index.html +++ b/index.html @@ -42,7 +42,6 @@ - @@ -52,10 +51,6 @@
SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion - - - -

@@ -68,22 +63,19 @@
Juncheng Hu1
- Jing Zhang1 + Jing + Zhang1
- Dong Xu2 + Dong + Xu2
- Qian Yu1 + Qian + Yu1
- - - - - -
@@ -91,35 +83,39 @@
+ +
-
- -
+
svgfusion teaser
Noteworthy characteristics of the SVGs generated by our new method include: @@ -147,11 +143,11 @@

Abstract

The generation of Scalable Vector Graphics (SVG) assets from textual data remains a significant challenge, largely due to the scarcity of high-quality vector datasets and the limitations in scalable vector representations required for modeling intricate graphic distributions. This work introduces - SVGFusion, a Text-to-SVG model capable of scaling to real-world SVG data without reliance on a + SVGFusion, a Text-to-SVG model capable of scaling to real-world SVG data without reliance on a text-based discrete language model or prolonged SDS optimization. The essence of SVGFusion is to learn a continuous latent space for vector graphics with a popular Text-to-Image framework. Specifically, - SVGFusion consists of two modules: a Vector-Pixel Fusion Variational Autoencoder - (VP-VAE) and a Vector + SVGFusion consists of two modules: a Vector-Pixel Fusion Variational Autoencoder + (VP-VAE) and a Vector Space Diffusion Transformer (VS-DiT). VP-VAE takes both the SVGs and corresponding rasterizations as inputs and learns a continuous latent space, whereas VS-DiT learns to generate a latent code within this @@ -336,7 +332,7 @@

Experiments

- experiments
Qualitative Comparison of SVGFusion and Existing Text-to-SVG Methods. The @@ -408,15 +404,15 @@

Bibtex


-
-
-

Acknowledgements

-

We thank Ximing Xing for providing us with the - source code of the web page to help us - build the project home page.

-
-
-
+ + + + + + + + +