Skip to content

Commit

Permalink
Update index.html
Browse files Browse the repository at this point in the history
  • Loading branch information
@HannahHaensen
HannahHaensen committed Mar 25, 2024
1 parent 0c50cb8 commit 7d042a8
Showing 1 changed file with 157 additions and 146 deletions.
303 changes: 157 additions & 146 deletions docs/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -116,183 +116,194 @@
<body>
<section style="background: rgba(25, 12, 12, 0.04)">
<div class="container">
<br>
<br>
<br>
<br>
<h1 style="align-content: center; text-align: center"><i>V2: </i>DynaMoN: Motion-Aware Fast And Robust Camera
Localization for Dynamic Neural Radiance Fields</h1>
<h5 style="align-content: center; text-align: center"><i>V1: </i>DynaMoN: Motion-Aware Fast And Robust Camera
Localization for Dynamic NeRF</h1>
<div class="row" style="align-content: center; text-align: center">
<div class="col-md-12">
<b> Nicolas Schischka* (1), Hannah Schieber* (2,4), Mert Asim Karaoglu* (1,3), Melih Gorgulu* (1),
<br> Florian Grotzner (1), Alexander Ladikos (3), Daniel Roth (4), Nassir Navab (1,5) and Benjamin
Busam (1)</b>
<p>* indicates equal contribution</p>
<br>
<br>
<br>
<br>
<h1 style="align-content: center; text-align: center"><i>V2: </i>DynaMoN: Motion-Aware Fast And Robust Camera
Localization for Dynamic Neural Radiance Fields</h1>
<h5 style="align-content: center; text-align: center"><i>V1: </i>DynaMoN: Motion-Aware Fast And Robust Camera
Localization for Dynamic NeRF</h5>
<div class="row" style="align-content: center; text-align: center">
<div class="col-md-12">
<b> Nicolas Schischka* (1), Hannah Schieber* (2,4), Mert Asim Karaoglu* (1,3), Melih Gorgulu* (1),
<br> Florian Grotzner (1), Alexander Ladikos (3), Daniel Roth (4), Nassir Navab (1,5) and
Benjamin
Busam (1)</b>
<p>* indicates equal contribution</p>

</div>
</div>

</div>
<div class="row" style="align-content: center; text-align: center">
<div class="col-md-2 col-sm-6">
Technical University of Munich, <br>
Munich, Germany
<sup>1</sup>
</div>
<div class="row" style="align-content: center; text-align: center">
<div class="col-md-2 col-sm-6">
Technical University of Munich, <br>
Munich, Germany
<sup>1</sup>
</div>

<div class="col-md-2 col-sm-6">
Friedrich-Alexander Universitat Erlangen-Nürnberg, <br> Erlangen, Germany
<sup>2</sup>
</div>
<div class="col-md-2 col-sm-6">
Friedrich-Alexander Universitat Erlangen-Nürnberg, <br> Erlangen, Germany
<sup>2</sup>
</div>

<div class="col-md-2 col-sm-6">
ImFusion GmbH, <br>Munich, Germany
<sup>3</sup>
</div>
<div class="col-md-3 col-sm-6">
Technical University of Munich, School of Medicine and Health, Klinikum rechts der Isar, Orthopaedics and
Sports Orthopaedics, Munich, Germany
<sup>4</sup>
</div>
<div class="col-md-2 col-sm-6">
ImFusion GmbH, <br>Munich, Germany
<sup>3</sup>
</div>
<div class="col-md-3 col-sm-6">
Technical University of Munich, School of Medicine and Health, Klinikum rechts der Isar,
Orthopaedics and
Sports Orthopaedics, Munich, Germany
<sup>4</sup>
</div>

<div class="col-md-3 col-sm-6">
Johns Hopkins University, Baltimore, MD, USA
<sup>4</sup>
</div>
<div class="col-md-3 col-sm-12">
<div class="col-md-3 col-sm-6">
Johns Hopkins University, Baltimore, MD, USA
<sup>4</sup>
</div>
<div class="col-md-3 col-sm-12">

</div>
</div>
</div>
<div class="row" style="align-content: center; text-align: center">
<div class="row" style="align-content: center; text-align: center">

<div class=" col-lg-6 col-md-12 col-sm-12">
<a href="https://arxiv.org/pdf/2309.08927.pdf">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/paper.png?raw=true"
style="width: 50px; border: 1px black solid"></a>
<p>arixv</p>
</div>
<div class=" col-lg-6 col-md-12 col-sm-12">
<a href="https://github.com/HannahHaensen/DynaMoN">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/github.png?raw=true"
style="width: 50px;"></a>
<p>Code (coming soon)</p>
<div class=" col-lg-6 col-md-12 col-sm-12">
<a href="https://arxiv.org/pdf/2309.08927.pdf">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/paper.png?raw=true"
style="width: 50px; border: 1px black solid"></a>
<p>arixv</p>
</div>
<div class=" col-lg-6 col-md-12 col-sm-12">
<a href="https://github.com/HannahHaensen/DynaMoN">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/github.png?raw=true"
style="width: 50px;"></a>
<p>Code (coming soon)</p>
</div>
</div>
</div>
</div>
</section>
<section>
<div class="container">
<br>
<div class="row" style="align-content: center;">
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center">
<h5>COLMAP + HexPlane</h5>
<img width="350" height="263"
src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_1_.gif?raw=true">
</div>
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center">
<h5>DynaMoN</h5>
<img width="350" height="263"
src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_2_.gif?raw=true">
</div>
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center;">
<h5>Compare</h5>
<div class="img-comp-container">
<div class="img-comp-img">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_1_.gif?raw=true"
width="350" height="263">
</div>
<div class="img-comp-img img-comp-overlay">
<img id="imageid" src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_2_.gif?raw=true"
width="350" height="263">
<br>
<div class="row" style="align-content: center;">
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center">
<h5>COLMAP + HexPlane</h5>
<img width="350" height="263"
src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_1_.gif?raw=true">
</div>
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center">
<h5>DynaMoN</h5>
<img width="350" height="263"
src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_2_.gif?raw=true">
</div>
<div class="col-lg-4 col-md-4 col-sm-12" style="align-content: center; text-align: center;">
<h5>Compare</h5>
<div class="img-comp-container">
<div class="img-comp-img">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_1_.gif?raw=true"
width="350" height="263">
</div>
<div class="img-comp-img img-comp-overlay">
<img id="imageid"
src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/rgbd_dataset_freiburg3_walking_static-_2_.gif?raw=true"
width="350" height="263">
</div>
</div>
</div>
</div>
</div>
<br>
<br>
<br>
<p>We present DynaMoN, a motion aware fast and robust camera localization approach for novel view synthesis.
DynaMoN can handle not only the motion of known objects
using semantic segmentation masks but also that of unknown objects using a motion segmentation mask.
Furthermore, it retrieves the camera poses faster and more robust compared to classical SfM approaches enabling
a more accurate
4D scene representation. Compared to the state-of-the-art, DynaMoN outperforms other dynamic camera localization
approaches and shows better results for novel view synthesis.</p>
<br>



<br>
<p>We present DynaMoN, a motion aware fast and robust camera localization approach for novel view synthesis.
DynaMoN can handle not only the motion of known objects
using semantic segmentation masks but also that of unknown objects using a motion segmentation mask.
Furthermore, it retrieves the camera poses faster and more robust compared to classical SfM approaches
enabling
a more accurate
4D scene representation. Compared to the state-of-the-art, DynaMoN outperforms other dynamic camera
localization
approaches and shows better results for novel view synthesis.</p>
<br>

<div class="row">
<h3>Abstract</h3>
</div>
<div class="row">

<div class="col-lg-6 col-md-6 col-sm-12">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/teaser_.png?raw=true"
style="width: 80%">
<div class="row">
<h3>Abstract</h3>
</div>
<div class="row">

<div class="col-lg-6 col-md-6 col-sm-12">
<br>
<p>
Dynamic reconstruction with neural radiance fields (NeRF) requires accurate camera poses. These are
often hard to retrieve with existing structure-from-motion (SfM) pipelines as both camera and scene
content can change. We
propose DynaMoN that leverages simultaneous localization and mapping (SLAM) jointly with motion masking
to handle dynamic scene content. Our robust SLAM-based tracking module
significantly accelerates the training process of the dynamic NeRF while improving the quality of
synthesized views at the same time. Extensive experimental validation on TUM RGB-D, BONN RGB-D Dynamic
and the DyCheck’s iPhone dataset, three real-world datasets, shows the advantages of DynaMoN both for
camera pose estimation and novel view synthesis.
</p>
<div class="col-lg-6 col-md-6 col-sm-12">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/teaser_.png?raw=true"
style="width: 80%">
</div>

<div class="col-lg-6 col-md-6 col-sm-12">
<br>
<p>
Dynamic reconstruction with neural radiance fields (NeRF) requires accurate camera poses. These are
often hard to retrieve with existing structure-from-motion (SfM) pipelines as both camera and scene
content can change. We
propose DynaMoN that leverages simultaneous localization and mapping (SLAM) jointly with motion
masking
to handle dynamic scene content. Our robust SLAM-based tracking module
significantly accelerates the training process of the dynamic NeRF while improving the quality of
synthesized views at the same time. Extensive experimental validation on TUM RGB-D, BONN RGB-D
Dynamic
and the DyCheck’s iPhone dataset, three real-world datasets, shows the advantages of DynaMoN both
for
camera pose estimation and novel view synthesis.
</p>
</div>
</div>
</div>
<br>
<br>
<div class="row">
<h3>Architecture</h3>
<div class="col-md-12" style="align-content: center; text-align: center">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/arch.png?raw=true"
style="width: 80%">
<br>
<br>
<div class="row">
<h3>Architecture</h3>
<div class="col-md-12" style="align-content: center; text-align: center">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/arch.png?raw=true"
style="width: 80%">
</div>
</div>
</div>
<br>
<br>
<div class="row">
<h3>Results</h3>
</div>
<div class="row">
<h5>Visual Improvements</h5>
<br>
<div class="col-md-12">
<p>DynaMoN enables better visual results in dynamic scenes.</p>
<br>
<div class="row">
<h3>Results</h3>
</div>
<div class="col-md-12" style="align-content: center; text-align: center">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/results.png?raw=true"
style="width: 80%">
<div class="row">
<h5>Visual Improvements</h5>
<br>
<div class="col-md-12">
<p>DynaMoN enables better visual results in dynamic scenes.</p>
</div>
<div class="col-md-12" style="align-content: center; text-align: center">
<img src="https://github.com/HannahHaensen/DynaMoN/blob/gh-pages/docs/assets/res.png?raw=true"
style="width: 80%">
</div>
</div>
</div>
<br>
<br>
<br>
<br>

<h3>Citation</h3>
<div class="row">
<div class="col-md-12">
<p style="background: lightgray; margin: 10px; padding: 10px;">
@misc{@misc{2023DynaMoN,<br>
&nbsp&nbsptitle={DynaMoN: Motion-Aware Fast And Robust Camera Localization for Dynamic NeRF},<br>
&nbsp&nbspauthor={Karaoglu, Mert Asim and Schieber, Hannah and Schischka, Nicolas and
G{\"o}rg{\"u}l{\"u}, Melih and Gr{\"o}tzner, Florian and Ladikos, Alexander and Roth, Daniel and Navab,
Nassir and Busam, Benjamin},<br>
&nbsp&nbspjournal={arXiv preprint arXiv:2309.08927},<br>
&nbsp&nbspyear={2023}<br>
}
</p>
<h3>Citation</h3>
<div class="row">
<div class="col-md-12">
<p style="background: lightgray; margin: 10px; padding: 10px;">

@misc{schischka2024dynamon,<br>
&nbsp&nbsp title={DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural
Radiance Fields}, <br>
&nbsp&nbsp author={Nicolas Schischka and Hannah Schieber and Mert Asim Karaoglu and Melih Görgülü
and Florian Grötzner and Alexander Ladikos and Daniel Roth and Nassir Navab and Benjamin Busam},<br>
&nbsp&nbsp year={2024},<br>
&nbsp&nbsp eprint={2309.08927},<br>
&nbsp&nbsp archivePrefix={arXiv},<br>
&nbsp&nbsp primaryClass={cs.CV}<br>
}
</p>
</div>
</div>
</div>
</div>
<br>
<br>
</section>
<script>
/*Execute the Function*/
Expand Down

0 comments on commit 7d042a8

Please sign in to comment.