Skip to content

Commit

Permalink
docs
Browse files Browse the repository at this point in the history
  • Loading branch information
@jiaoyining
jiaoyining committed Apr 16, 2024
1 parent 6b1a39d commit 5464e32
Show file tree
Hide file tree
Showing 21 changed files with 3,304 additions and 0 deletions.
221 changes: 221 additions & 0 deletions docs/index.html
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,221 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="description"
content="Deformable Neural Radiance Fields creates free-viewpoint portraits (nerfies) from casually captured videos.">
<meta name="keywords" content="Nerfies, D-NeRF, NeRF">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts</title>

<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PYVRSFMDRL"></script>
<script>
window.dataLayer = window.dataLayer || [];

function gtag() {
dataLayer.push(arguments);
}

gtag('js', new Date());

gtag('config', 'G-PYVRSFMDRL');
</script>

<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
rel="stylesheet">

<link rel="stylesheet" href="./static/css/bulma.min.css">
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet"
href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="icon" href="./static/images/favicon.svg">

<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
<script src="./static/js/bulma-slider.min.js"></script>
<script src="./static/js/index.js"></script>
</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">
<h2 class="title is-2 publication-title">Rethinking Interactive Image Segmentation <br> with Low Latency, High Quality, and Diverse Prompts</h2>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://sites.google.com/cs.unc.edu/qinliu/home">Qin Liu</a>,</span>
<span class="author-block">
<a href="https://j-min.io">Jaemin Cho</a>,</span>
<span class="author-block">
<a href="https://www.cs.unc.edu/~mbansal/">Mohit Bansal</a>,</span>
<span class="author-block">
<a href="https://biag.cs.unc.edu/">Marc Niethammer</a></span>
</div>

<div class="is-size-5 publication-authors">
<span class="author-block">University of North Carolina at Chapel Hill</span> <br>
<span class="author-block">CVPR 2024</span>
</div>

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<a href="https://arxiv.org/abs/2404.00741"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span>
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/uncbiag/SegNext"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>
</div>
</div>
</div>
</div>
</div>
</div>
</section>

<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<center><img src="./static/images/teaser.png" width="750"></center>
<!-- <h2 class="subtitle has-text-centered"> -->
<!-- We propose <span class="dnerf">SegNext</span> for next-generation promptable segmentation <br> with low latency, high quality, and diverse prompts. -->
Conceptual comparison between our approach <span class="dnerf">SegNext</span> and prior state-of-the-art methods, SimpleClick and
SAM, for the interactive segmentation task. Our method combines the best of both worlds for interactive segmentation with low
latency, high quality, and diverse prompts.

<!-- </h2> -->
</div>
</div>
</section>

<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<center>
<img src="./static/images/medal.gif" width=220>
<img src="./static/images/bicyclestand.gif" width=317>
<img src="./static/images/crack.gif" width=220>
</center>
<!-- <h2 class="subtitle has-text-centered"> -->
<center>Demos of <span class="dnerf">SegNext</span> for high-quality segmentation on HQSeg-44K with One Click.</center>
<!-- </h2> -->
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<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>
The goal of interactive image segmentation is to delineate specific regions
within an image via visual or language prompts. Low-latency and high-quality
interactive segmentation with diverse prompts remain challenging for existing
specialist and generalist models. Specialist models, with their limited
prompts and task-specific designs, experience high latency because the image
must be recomputed every time the prompt is updated, due to the joint
encoding of image and visual prompts. Generalist models, exemplified by the
Segment Anything Model (SAM), have recently excelled in prompt diversity and
efficiency, lifting image segmentation to the foundation model era.
However, for high-quality segmentations, SAM still lags behind state-of-the-art
specialist models despite SAM being trained with ×100 more
segmentation masks.
</p>
<p>
In this work, we delve deep into the
architectural differences between the two types of models.
We observe that dense representation and fusion of visual
prompts are the key design choices contributing to the high
segmentation quality of specialist models. In light of this,
we reintroduce this dense design into the generalist models, to facilitate the development of generalist models with
high segmentation quality. To densely represent diverse visual prompts, we propose to use a dense map to capture
five types: clicks, boxes, polygons, scribbles, and masks.
</p>
<p>
Thus, we propose SegNext, a next-generation interactive
segmentation approach offering low latency, high quality,
and diverse prompt support. Our method outperforms current state-of-the-art methods on HQSeg-44K and DAVIS,
both quantitatively and qualitatively.
</p>
</div>
</div>
</div>
</div>
</section>


<section class="section">
<div class="container is-max-desktop">
<center><h2 class="title is-3">Method</h2></center>
<center><img src="./static/images/method.png"></center>
SegNext overview. We use a three-channel dense map to represent five diverse visual prompts: clicks, boxes, polygons, scribbles,
and masks. The embeddings of image and visual prompts are fused by element-wise addition, followed by an enhanced fusion via one
or two self-attention blocks. The language prompt is encoded as a vector by CLIP, followed by querying the image embedding via
cross-attention blocks for the mask embeddings. A lightweight decoder processes the mask embeddings for segmentation.
</div>
</section>



<section class="section">
<div class="container is-max-desktop">
<center><h2 class="title is-3">Experiments</h2></center><br>
<center><img src="./static/images/result_click_curve.png"></center>
Click to segmentation evaluation on HQSeg-44K and DAVIS. With varying numbers of clicks, our method consistently outperforms
existing competitive approaches. The metric is mean Intersection over Union (mIoU).

<br><br><br>

<center><img src="./static/images/result_quanti_table.png"></center>
Quantitative comparison with existing methods on HQSeg-44K and DAVIS. We compare two types of baselines: specialist and
generalist models. Our model achieves comparable performance to the specialist baselines but with significantly lower latency; our model
achieves comparable performance to the generalist models in terms of latency and segmentation quality despite being trained with much
fewer segmentation data. “HQ” denotes the HQSeg-44K dataset; “SA×2” denotes the model has two self-attention blocks for dense fusion.

<br><br><br>

<center><img src="./static/images/result_qualitative.png"></center>
Qualitative results with diverse prompts. Left: an example from DAVIS. Right: three examples from HQSeg-44K. The results
are achieved by a user providing all the prompts using our best-performing model.

</div>
</section>


<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article{liu2024rethinking,
author = {Liu, Qin and Cho, Jaemin and Bansal, Mohit and Niethammer, Marc},
title = {Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts},
journal = {CVPR},
year = {2024},
}</code></pre>
</div>
</section>

</body>
</html>
1 change: 1 addition & 0 deletions docs/static/css/bulma-carousel.min.css
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading

0 comments on commit 5464e32

Please sign in to comment.