Skip to content

Commit

Permalink
a
Browse files Browse the repository at this point in the history
  • Loading branch information
@martinsinnona
martinsinnona committed May 28, 2024
1 parent 57da61d commit 571ef74
Show file tree
Hide file tree
Showing 2 changed files with 449 additions and 24 deletions.
185 changes: 161 additions & 24 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,12 @@
<html>
<head>
<meta charset="utf-8">
<meta name="description" content="VisDecode: AI-Driven Interpretation and Enhancement of Scientific Plots">
<meta name="keywords" content="VisDecode, AI, Scientific Plots, Data Visualization">
<meta name="description"
content="DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling">
<meta name="keywords" content="DUDF, DiffUDF, Diff-UDF">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>VisDecode: AI-Driven Interpretation and Enhancement of Scientific Plots</title>
<link rel="icon" href="./assets/favicon.ico">
<title>DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling</title>
<link rel="icon" href="./assets/favicon-PpA8Xu1v.ico">

<!-- Global site tag (gtag.js) - Google Analytics -->
<!--script async src="https://www.googletagmanager.com/gtag/js?id=G-PYVRSFMDRL"></script-->
Expand All @@ -22,43 +23,48 @@
gtag('config', 'G-PYVRSFMDRL');
</script>

<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
rel="stylesheet">
<!-- Add the slick-theme.css if you want default styling -->
<link rel="stylesheet" type="text/css" href="//cdn.jsdelivr.net/gh/kenwheeler/[email protected]/slick/slick.css"/>
<!-- Add the slick-theme.css if you want default styling -->
<link rel="stylesheet" type="text/css" href="//cdn.jsdelivr.net/gh/kenwheeler/[email protected]/slick/slick-theme.css"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet"
href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<script src="https://kit.fontawesome.com/b814c174cf.js" crossorigin="anonymous"></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script type="module" crossorigin src="./assets/index.js"></script>
<link rel="stylesheet" crossorigin href="./assets/index.css">
<script type="module" crossorigin src="./assets/index-slEm1AaK.js"></script>
<link rel="stylesheet" crossorigin href="./assets/index-pgBFF5R7.css">
</head>
<body>


<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">VisDecode: AI-Driven Interpretation and Enhancement of Scientific Plots</h1>
<h1 class="title is-1 publication-title">DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://github.com/author1">Author One</a><sup>1</sup>,</span>
<a href="https://github.com/miguef98">Miguel Fainstein</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://github.com/author2">Author Two</a><sup>1</sup>,</span>
<a href="https://github.com/vsiless">Viviana Siless</a><sup>1</sup>,</span>
<span class="author-block">
<a href="https://author3.com/">Author Three</a><sup>1,2</sup>,
<a href="https://emmanueliarussi.github.io/">Emmanuel Iarussi</a><sup>1,2</sup>,
</span>
</div>

<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>University A</span>
<span class="author-block"><sup>2</sup>Institute B</span>
<span class="author-block"><sup>1</sup>Universidad Torcuato DiTella</span>
<span class="author-block"><sup>2</sup>CONICET</span>
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<a href="https://arxiv.org/pdf/xxxx.xxxxx.pdf"
<a href="https://arxiv.org/pdf/2402.08876.pdf"
target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
Expand All @@ -68,7 +74,7 @@ <h1 class="title is-1 publication-title">VisDecode: AI-Driven Interpretation and
</a>
</span>
<span class="link-block">
<a href="https://arxiv.org/abs/xxxx.xxxxx"
<a href="https://arxiv.org/abs/2402.08876"
target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
Expand All @@ -79,7 +85,7 @@ <h1 class="title is-1 publication-title">VisDecode: AI-Driven Interpretation and
</span>
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/VisDecode"
<a href="https://github.com/LIA-DiTella/DiffUDF"
target="_blank"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
Expand All @@ -88,6 +94,7 @@ <h1 class="title is-1 publication-title">VisDecode: AI-Driven Interpretation and
<span>Code</span>
</a>
</span>
</a>
</div>

</div>
Expand All @@ -101,32 +108,161 @@ <h1 class="title is-1 publication-title">VisDecode: AI-Driven Interpretation and
<div class="container is-max-desktop">
<div class="hero-body">
<h2 class="subtitle has-text-centered">
VisDecode is a project to create an AI tool capable of automatically interpreting and providing feedback on scientific plots. Utilizing state-of-the-art visual language understanding techniques, VisDecode analyzes raster images of plots such as bar charts, line charts, and scatter plots. It extracts key visual attributes like color, shape, positioning, and plot data, all of which significantly impact data perception and understanding. Based on these analyses and well-established best practices from data visualization literature, VisDecode offers actionable suggestions for improving the design of these plots. This feedback helps ensure that scientific visualizations are both clear and effective in communicating data. A significant advantage of VisDecode is its framework-free nature, allowing scientists to continue using their preferred visualization tools while still benefiting from AI-driven design enhancements. By incorporating these expert recommendations, VisDecode empowers researchers to create better data visualizations.
<span class="dnerf">DUDF</span> is able to leverage general-shape neural representation by learning a hyperbolic scaled unsigned distance field.
The learning process is governed by solving a new and interesting Eikonal problem.
This allows for detailed reconstructions, and extraction of important topological properties such as normal fields and shape curvatures; which were evasive in previous works.
</h2>
</div>
</div>
</section>

<section class="hero is-light is-small">
<div class="hero-body">
<div class="container is-max-desktop content">
<img src="./assets/teaser-1KX-P5JL.png"
class="interpolation-image"
alt="Interpolate start reference image."/>
</div>
</div>
</section>


<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In recent years, there has been a growing interest in training Neural Networks to approximate Unsigned Distance Fields (UDFs) for representing open surfaces in the context of 3D reconstruction.
However, UDFs are non-differentiable at the zero level set which leads to significant errors in distances and gradients, generally resulting in fragmented and discontinuous surfaces.
In this paper, we propose to learn a hyperbolic scaling of the unsigned distance field, which defines a new Eikonal problem with distinct boundary conditions.
This allows our formulation to integrate seamlessly with state-of-the-art continuously differentiable implicit neural representation networks, largely applied in the literature to represent signed distance fields.
Our approach not only addresses the challenge of open surface representation but also demonstrates significant improvement in reconstruction quality and training performance.
Moreover, the unlocked field's differentiability allows the accurate computation of essential topological properties such as normal directions and curvatures, pervasive in downstream tasks such as rendering.
Through extensive experiments, we validate our approach across various data sets and against competitive baselines.
The results demonstrate enhanced accuracy and up to an order of magnitude increase in speed compared to previous methods.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
</div>
</section>

<div id="meshes">
<canvas id="c"></canvas>
<div id="firstMesh" class="list-item">
<div id="firstScene" class="scene"></div>
</div>

<div id="secondMesh" class="list-item">
<div id="secondScene" class="scene"></div>
</div>

<div id="thirdMesh" class="list-item">
<div id="thirdScene" class="scene"></div>
</div>
</div>


<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column is-half">
<h2 class="title is-3">Baseline comparisons</h2>
<p>
We compare our method to state of the art neural representation approaches in three common open-surface datasets. Results show greater accuracy and improved training times.
<br><br>
</p>
<div class="container">
<div id="carousel">
<div><img src="./assets/comp1-OLb0rkec.png"/></div>
<div><img src="./assets/comp2-T8CwnHTZ.png"/></div>
<div><img src="./assets/comp3-O_SydRvz.png"/></div>
<div><img src="./assets/comp4-X2--LtZu.png"/></div>
<div><img src="./assets/comp5--OEK5SvC.png"/></div>
<div><img src="./assets/comp6--z1oVk79.png"/></div>
</div>
</div>

</div>

<div class="column is-half">
<h2 class="title is-3">Topological properties</h2>
<div class="columns is-centered">
<div class="column content is-max-desktop">
<p>
The full differentiability of our method allows for mean and gaussian curvature computation.
<br><br>
</p>
<img src="./assets/curvatures-baLI18X5.png"/>
<div class="armadillo is-centered has-text-centered">
<img src="./assets/arm_mean-Ep2H8l-B.gif"/>
<p>Mean</p>
</div>
<div class="armadillo is-centered has-text-centered">
<img src="./assets/arm_gauss-3ND8wPkI.gif"/>
<p>Gaussian</p>
</div>
</div>
</div>
</div>
</div>

<div class="columns is-centered">
<div class="column is-full-width is-max-desktop">
<h2 class="title is-3">Direct rendering and ilumination</h2>
<div class="content has-text-justified">
<p>
Precise normal field and principal curvatures computation allows for realistic direct rendering techniques.
</p>
</div>

<div class="columns is-vcentered is-">
<div class="column is-two-fifth">
<img src="./assets/max_planck-WNYGyvYa.gif"/>
</div>
<div class="column is-three-fifth">
<img src="./assets/bimba-B1bDB16P.gif"/>
</div>
</div>
<div class="columns is-vcentered">
<div class="column">
<img src="./assets/beetle-PpnP1lMX.gif"/>
</div>
<div class="column">
<img src="./assets/lounge-n7ueTtno.gif"/>
</div>
</div>
</div>
</div>
</div>
</section>


<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>
@misc{author2024visdecode,
title={VisDecode: AI-Driven Interpretation and Enhancement of Scientific Plots},
author={Author One and Author Two and Author Three},
@misc{fainstein2024dudf,
title={DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling},
author={Miguel Fainstein and Viviana Siless and Emmanuel Iarussi},
year={2024},
eprint={xxxx.xxxxx},
eprint={2402.08876},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
</code></pre>
</div>
</section>


<footer class="footer">
<div class="container">
<div class="content has-text-centered">
<a class="icon-link" href="https://github.com/author1" class="external-link">
<a class="icon-link" href="https://github.com/miguef98" class="external-link">
<i class="fab fa-github"></i>
</a>
</div>
Expand All @@ -137,7 +273,7 @@ <h2 class="title">BibTeX</h2>
Source code mainly borrowed from <a href="https://keunhong.com/">Keunhong Park</a>'s <a href="https://nerfies.github.io/">Nerfies website</a>.
</p>
<p>
Please contact <a href="https://github.com/author1">Author One</a> for feedback and questions.
Please contact <a href="https://github.com/miguef98">Miguel Fainstein</a> for feedback and questions.
</p>
</div>
</div>
Expand All @@ -149,3 +285,4 @@ <h2 class="title">BibTeX</h2>

</body>
</html>

Loading

0 comments on commit 571ef74

Please sign in to comment.