mirror of
https://github.com/OpenVGLab/OmniLottie.git
synced 2026-09-16 23:26:26 +00:00
Update website: add CVPR 2026 acceptance and assets
This commit is contained in:
OmniLottie
Binary file not shown.
|
After Width: | Height: | Size: 358 KiB |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 438 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 1.5 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 628 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 1.6 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 591 KiB |
+14
-36
@@ -212,6 +212,11 @@
|
||||
<span class="author-block"><sup>*</sup>Project Lead,</span>
|
||||
<span class="author-block"><sup>‡</sup>Correspondence Authors</span>
|
||||
</div>
|
||||
|
||||
<div class="is-size-3 publication-authors" style="margin-top: 15px;">
|
||||
<span style="font-weight: bold; color: #b39ddb;">Accepted by CVPR 2026</span>
|
||||
</div>
|
||||
|
||||
<div class="is-size-5 publication-authors">
|
||||
<span class="author-block"><sup>1</sup>Fudan University,</span>
|
||||
<span class="author-block"><sup>2</sup>StepFun,</span>
|
||||
@@ -317,7 +322,7 @@
|
||||
<h2 class="title is-4">Highlights</h2>
|
||||
<div class="columns is-centered" style="text-align: center">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-teaser.jpg" alt="OmniLottie Teaser">
|
||||
<img src="./assets/OmniLottie-teaser.png" alt="OmniLottie Teaser">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
@@ -334,7 +339,7 @@
|
||||
<h2 class="title is-4">Method Overview</h2>
|
||||
<div class="columns is-centered" style="text-align: center">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-pipeline.jpg" alt="OmniLottie Pipeline">
|
||||
<img src="./assets/OmniLottie-pipeline.png" alt="OmniLottie Pipeline">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
@@ -344,23 +349,6 @@
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Lottie Tokenizer Details -->
|
||||
<div class="columns is-centered" style="margin-top: 15px">
|
||||
<div class="column is-full-width">
|
||||
<h2 class="title is-4">Lottie Tokenizer</h2>
|
||||
<div class="columns is-centered" style="text-align: center">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-tokenizer.jpg" alt="Lottie Tokenizer">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
Our Lottie tokenizer converts raw JSON files into compact sequences of shape, effect, and animation commands with their associated parameters.
|
||||
This representation substantially shortens sequence lengths (81% reduction compared to raw JSON), improves token efficiency, and enables OmniLottie to learn a clean distribution over animation primitives.
|
||||
The tokenizer supports five fundamental layer types: Precomposition, Solid, Null, Shape, and Text layers, each identified by a unique type parameter.
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@@ -374,19 +362,19 @@
|
||||
<div id="post_images" class="carousel">
|
||||
<div class="item-1">
|
||||
<video poster="" autoplay="" muted loop="" style="pointer-events: none;">
|
||||
<source src="./assets/OmniLottie-demo-text2lottie.mp4" type="video/mp4">
|
||||
<source src="./assets/OmniLottie-demo-1.mp4" type="video/mp4">
|
||||
</video>
|
||||
<p class="has-text-centered"><b>Text-to-Lottie Generation</b></p>
|
||||
</div>
|
||||
<div class="item-2">
|
||||
<video poster="" autoplay="" muted loop="" style="pointer-events: none;">
|
||||
<source src="./assets/OmniLottie-demo-image2lottie.mp4" type="video/mp4">
|
||||
<source src="./assets/OmniLottie-demo-2.mp4" type="video/mp4">
|
||||
</video>
|
||||
<p class="has-text-centered"><b>Text-Image-to-Lottie Generation</b></p>
|
||||
</div>
|
||||
<div class="item-3">
|
||||
<video poster="" autoplay="" muted loop="" style="pointer-events: none;">
|
||||
<source src="./assets/OmniLottie-demo-video2lottie.mp4" type="video/mp4">
|
||||
<source src="./assets/OmniLottie-demo-3.mp4" type="video/mp4">
|
||||
</video>
|
||||
<p class="has-text-centered"><b>Video-to-Lottie Generation</b></p>
|
||||
</div>
|
||||
@@ -415,7 +403,7 @@
|
||||
</div>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-t2lottie.jpg" alt="Text-to-Lottie Comparison">
|
||||
<img src="./assets/OmniLottie-t2lottie.png" alt="Text-to-Lottie Comparison">
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -425,7 +413,7 @@
|
||||
</div>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-ti2lottie.jpg" alt="Text-Image-to-Lottie Comparison">
|
||||
<img src="./assets/OmniLottie-ti2lottie.png" alt="Text-Image-to-Lottie Comparison">
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -435,7 +423,7 @@
|
||||
</div>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-v2lottie.jpg" alt="Video-to-Lottie Comparison">
|
||||
<img src="./assets/OmniLottie-v2lottie.png" alt="Video-to-Lottie Comparison">
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -445,11 +433,6 @@
|
||||
<div class="columns is-centered" style="margin-top: 20px">
|
||||
<div class="column is-full-width">
|
||||
<h2 class="title is-4">Quantitative Results</h2>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-quantitative-table.jpg" alt="Quantitative Results">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
OmniLottie achieves 97.3%, 92.0%, and 90.7% success rates for Text-to-Lottie, Text-Image-to-Lottie, and Video-to-Lottie tasks respectively,
|
||||
substantially outperforming all baselines while producing richer token sequences that enable more expressive and detailed vector animation generation.
|
||||
@@ -461,11 +444,6 @@
|
||||
<div class="columns is-centered" style="margin-top: 20px">
|
||||
<div class="column is-full-width">
|
||||
<h3 class="title is-4">MMLottie-2M Dataset</h3>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/MMLottie-dataset.jpg" alt="MMLottie-2M Dataset">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
The MMLottie-2M dataset consists of two million Lottie animations paired with multi-modal annotations including text descriptions, keyframe images, and rendered videos.
|
||||
Data is collected from major online platforms (LottieFiles, IconScout, Flaticon, Iconfont, Icons8) and augmented with SVG-derived animations.
|
||||
@@ -480,7 +458,7 @@
|
||||
<h3 class="title is-4">Data Processing Pipeline</h3>
|
||||
<div class="columns is-centered">
|
||||
<div class="column" style="align-self: center">
|
||||
<img src="./assets/OmniLottie-data-pipeline.jpg" alt="Data Processing Pipeline">
|
||||
<img src="./assets/OmniLottie-data-pipeline.png" alt="Data Processing Pipeline">
|
||||
</div>
|
||||
</div>
|
||||
<div class="content has-text-justified" style="padding-top: 15px">
|
||||
|
||||
Reference in New Issue
Block a user