Skip to content

Commit

Permalink
fix(index): update style
Browse files Browse the repository at this point in the history
  • Loading branch information
ximinng committed Dec 15, 2024
1 parent b286d3c commit 9ccd30e
Showing 1 changed file with 39 additions and 43 deletions.
82 changes: 39 additions & 43 deletions index.html
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,6 @@
<meta name="description"
content="SVGFusion, svgfusion, SVG generation, text-to-svg, text2svg, latent svg generation">
<!-- favicon -->
<!-- <link rel="icon" href="assets/favicon.png" type="image/x-icon">-->
<link rel="icon" href="assets/crown.svg" type="image/x-icon">
</head>

Expand All @@ -52,10 +51,6 @@
<!-- Paper Title -->
<div class="container text-center">
<span class="title-font x-gradient-font">SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion</span>
<!-- <a class="title-font text-body-emphasis"-->
<!-- href="#">-->
<!-- Paper Title-->
<!-- </a>-->
</div>
<hr>
<!-- author list -->
Expand All @@ -68,58 +63,59 @@
</div>
<div class="col-12 col-md-2">Juncheng Hu<sup>1</sup></div>
<div class="col-12 col-md-2">
<a class="link" href="https://hellojing89.github.io">Jing Zhang</a><sup>1</sup>
<a class="link" href="https://scholar.google.ch/citations?user=XtwOoQgAAAAJ&hl=en">Jing
Zhang</a><sup>1</sup>
</div>
<div class="col-12 col-md-2">
<a class="link" href="https://www.cs.hku.hk/people/academic-staff/dongxu">Dong Xu</a><sup>2</sup>
<a class="link" href="https://scholar.google.com.sg/citations?user=7Hdu5k4AAAAJ&hl=en">Dong
Xu</a><sup>2</sup>
</div>
<div class="col-12 col-md-2">
<a class="link" href="https://yuqian1023.github.io">Qian Yu</a><sup>1</sup>
<a class="link" href="https://scholar.google.com/citations?user=mmm90qgAAAAJ&hl=zh-CN">Qian
Yu</a><sup>1</sup>
</div>
<div class="col-12 col-md-1"></div>
</div>
<!-- <div class="row" style="margin-top: -0.5rem;">-->
<!-- <div class="col-12 col-md">-->
<!-- <a class="link" href="#">Dong Xu</a><sup>2</sup>-->
<!-- </div>-->
<!-- <div class="col-12 col-md">Qian Yu<sup>2</sup></div>-->
<!-- </div>-->
<!-- author organization -->
<div class="row mt-3">
<div class="col-12">
<sup>1</sup>Beihang University &nbsp;&nbsp;<sup>2</sup>The University of Hong Kong
</div>
</div>
</div>

<!-- paper status -->
<!-- <div class="text-center" style="margin-top: 20px">-->
<!-- <h3>Paper status - Under Review</h3>-->
<!-- </div>-->

<!-- links -->
<div class="text-center">
<div class="row justify-content-md-center">
<div id="links">
<div class="col col-lg-2">
<a id="paper" href="">Paper</a>
</div>
<div class="col col-lg-2">
<a id="arxiv" href="">Arxiv</a>
</div>
<div class="col col-lg-2">
<a id="code" href="https://github.com/ximinng/SVGFusion">Code</a>
</div>
<div class="col col-lg-2">
<a id="demo" href="https://huggingface.co/datasets/xingxm/SVG-Color-Emoji-Dataset">Dataset</a>
</div>
<div class="row justify-content-md-center" id="links">
<!-- <div class="col col-lg-2">-->
<!-- <a id="paper" href="#">Paper</a>-->
<!-- </div>-->

<!-- Arxiv Link -->
<div class="col col-lg-2">
<a id="arxiv" href="#">Arxiv</a>
</div>
<!-- Code Link -->
<div class="col col-lg-2">
<a id="code" href="https://github.com/ximinng/SVGFusion">Code</a>
<div style="margin-top: -0.5rem;">(coming soon)</div>
</div>
<!-- <div class="col col-lg-2">-->
<!-- <a id="demo" href="https://huggingface.co/datasets/xingxm/SVG-Color-Emoji-Dataset">Dataset</a>-->
<!-- </div>-->
</div>
</div>
<br>

<!-- teaser -->
<div class="text-center">
<figure class="figure">
<img src="assets/teaser.png" class="img-thumbnail figure-img img-fluid rounded"
style="width: 72%"
style="width: 90%"
alt="svgfusion teaser">
<figcaption class="figure-caption">
Noteworthy characteristics of the SVGs generated by our new method include:
Expand Down Expand Up @@ -147,11 +143,11 @@ <h2 class="card-title text-center card-title-margin">Abstract</h2>
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
<b style="color: #7e57c2">SVGFusion</b>, 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 <b>Vector-Pixel Fusion Variational Autoencoder
(VP-VAE)</b> and a <b>Vector
SVGFusion consists of two modules: a <b style="color: #7e57c2">Vector-Pixel Fusion Variational Autoencoder
(VP-VAE)</b> and a <b style="color: #7e57c2">Vector
Space Diffusion Transformer (VS-DiT)</b>. 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
Expand Down Expand Up @@ -336,7 +332,7 @@ <h2 class="card-title card-title-margin">Experiments</h2>

<div class="text-center">
<figure class="figure">
<img src="./assets/compare_t2svg.png" class="img-thumbnail figure-img img-fluid rounded"
<img src="./assets/compare_t2svg.png" class="figure-img img-fluid rounded"
alt="experiments">
<figcaption class="figure-caption">
<strong>Qualitative Comparison of SVGFusion and Existing Text-to-SVG Methods.</strong> The
Expand Down Expand Up @@ -408,15 +404,15 @@ <h1 class="modal-title fs-5" id="exampleModalLabel">Bibtex</h1>
<br>

<!-- Acknowledgements -->
<div class="card" style="border: none">
<div class="card-body">
<h4 class="card-title card-title-margin">Acknowledgements</h4>
<p class="card-text">We thank <a href="https://ximinng.github.io/">Ximing Xing</a> for providing us with the
source code of the web page to help us
build the project home page.</p>
</div>
</div>
<br>
<!-- <div class="card" style="border: none">-->
<!-- <div class="card-body">-->
<!-- <h4 class="card-title card-title-margin">Acknowledgements</h4>-->
<!-- <p class="card-text">We thank <a href="https://ximinng.github.io/">Ximing Xing</a> for providing us with the-->
<!-- source code of the web page to help us-->
<!-- build the project home page.</p>-->
<!-- </div>-->
<!-- </div>-->
<!-- <br>-->

</main>

Expand Down

0 comments on commit 9ccd30e

Please sign in to comment.