Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
yxbian23 committed Aug 25, 2024
1 parent d9aaa5b commit ab1cdcd
Showing 1 changed file with 1 addition and 84 deletions.
85 changes: 1 addition & 84 deletions index.html
Original file line number Diff line number Diff line change
Expand Up @@ -1630,90 +1630,7 @@ <h3 style="text-align: center; margin-bottom:20px">Comparing with Baselines in M
</div>
</div>

<div style="margin-top:50px; padding: 0px !important">
<h3 style="text-align: center; margin-bottom:20px">Multimodal Video Generation Application with Our
Generated Motions
</h3>
<div tab-content figure>
<div class="tab-pane fade show active" id="h36m" role="tabpanel" style="padding: 0px !important">
<div class="h-100 d-flex align-items-center justify-content-center">
<div class="dropdown list-group">
<button class="btn dropdown-toggle" style="max-width:600px" type="button" id="h36m-btn"
data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
<span class="selection">Music-Condition</span>
</button>
<div class="dropdown-menu" aria-labelledby="dropdownMenuButton" id="list-tab" role="tablist">
<a class="dropdown-item dropdown-item-action" href="#Music-Condition" id="h36m-dropdown" data-toggle="list"
role="tab" aria-controls="Music-Condition">Music-Condition</a>
<a class="dropdown-item dropdown-item-action" href="#Speech-Condition" id="h36m-dropdown" data-toggle="list"
role="tab" aria-controls="Speech-Condition">Speech-Condition</a>
<!-- <a class="dropdown-item dropdown-item-action" href="#case-3" id="h36m-dropdown" data-toggle="list"
role="tab" aria-controls="case-3">case-3</a> -->
</div>
</div>
</div>
<div class="card" style="padding: 10px !important; margin-top:10px">
<div class="tab-content figure" id="nav-tabContent">
<div class="tab-pane fade show active gif" id="Music-Condition" role="tabpanel">
<div style="display: flex; justify-content: space-around;">
<div style="width: 49%;">
<a style="text-align: center; display: inline-block; width: 100%;">Music Clip1</a>
<!-- <img class="webm" src="./assets/img/baseline/t2m_trip_fine.webm" > -->
<video width="100%" controls>
<source src="./assets/img/app/dance-1-mimic.mp4" type="video/webm">
</video>
</div>
<div style="width: 49%;">
<a style="text-align: center; display: inline-block; width: 100%;">Music Clip2</a>
<!-- <img class="webm" src="./assets/img/baseline/t2m_jump_our.webm"> -->
<video width="100%" controls>
<source src="./assets/img/app/dance-2-mimic.mp4" type="video/webm">
</video>
</div>
</div>
<!-- <div style="text-align: justify; width: 100%">
<a style='text-align: justify;width:49%; display: inline-block; text-align: center'>T2M-GPT</a>
<a style='text-align: justify;width:49%; display: inline-block; text-align: center'>HumanTOMATO</a>
</div>
<img class="gif" src="assets/img/baseline/back-gpt.gif" style='width:49%'>
<img class="gif" src="assets/img/baseline/back-ours.gif" style='width:49%'>
-->
<!-- <p style="text-align: center; color:purple"><b><i>A person is giving a speech, and the content is ...</i></b></p> -->
</div>

<div class="tab-pane fade" id="Speech-Condition" role="tabpanel">
<div style="display: flex; justify-content: space-around;">
<div style="width: 49%;">
<a style="text-align: center; display: inline-block; width: 100%;">Speech Segment1</a>
<!-- <img class="webm" src="./assets/img/baseline/t2m_trip_fine.webm" > -->
<video width="100%" controls>
<source src="./assets/img/app/speech-1-messe.mp4" type="video/webm">
</video>
</div>
<div style="width: 49%;">
<a style="text-align: center; display: inline-block; width: 100%;">Speech Segment2</a>
<!-- <img class="webm" src="./assets/img/baseline/t2m_jump_our.webm"> -->
<video width="100%" controls>
<source src="./assets/img/app/speech-2-messe.mp4" type="video/webm">
</video>
</div>
</div>


<!-- <p style="text-align: center; color:purple"><b><i>A person is giving a speech, and the content is ...</i></b></p> -->
</div>



<p style="text-align: justify; margin: 10px;">
Our generated motion sequences can be combined with any off-the-shelf human video generation framework, such as <a href="https://github.com/Tencent/MimicMotion">MimicMotion</a>, <a href="https://github.com/HumanAIGC/AnimateAnyone">AnimateAnyone</a>, and <a href="https://github.com/Kelu007/VividPose">VividPose</a>, enabling users to customize videos of any character based on specific control signals, such as speech or music.
Notably, unlike the traditional 2D keypoints estimated from videos, our generated 3D motion approach allows for flexible adjustment of camera parameters to project different visible body regions (e.g., full body or upper body)
</p>
</div>
</div>
</div>
</div>
</div>

<!-- <div style="margin-top:50px; padding: 0px !important">
<h3 style="text-align: center; margin-bottom:20px">How does Motion-aware language prior help the motion
generation?
Expand Down

0 comments on commit ab1cdcd

Please sign in to comment.