Skip to content

Commit 77b9187

Browse files
CaesarrWANGCaesarrWANG
authored
Add files via upload
0 parents  commit 77b9187

9 files changed

Lines changed: 469 additions & 0 deletions

File tree

‎index.html‎

Lines changed: 304 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,304 @@
1+
<!DOCTYPE html>
2+
<html>
3+
4+
<head>
5+
<meta charset="utf-8">
6+
<meta name="description"
7+
content="3DXTalker: An Integrated Framework for Expressive 3D Talking Avatars">
8+
<meta name="keywords" content="3D facial animation, speech-driven animation, talking avatars, identity modeling">
9+
<meta name="viewport" content="width=device-width, initial-scale=1">
10+
<title>3DXTalker: An Integrated Framework for Expressive 3D Talking Avatars</title>
11+
12+
<!-- Google tag (gtag.js) -->
13+
<script async src="https://www.googletagmanager.com/gtag/js?id=G-5T47ZCSTXZ"></script>
14+
<script>
15+
window.dataLayer = window.dataLayer || [];
16+
function gtag(){dataLayer.push(arguments);}
17+
gtag('js', new Date());
18+
19+
gtag('config', 'G-5T47ZCSTXZ');
20+
</script>
21+
22+
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">
23+
24+
<link rel="stylesheet" href="./static/css/bulma.min.css">
25+
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css">
26+
<link rel="stylesheet" href="./static/css/bulma-slider.min.css">
27+
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
28+
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
29+
<link rel="stylesheet" href="./static/css/index.css">
30+
<link rel="icon" href="./static/images/favicon.svg">
31+
32+
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
33+
<script defer src="./static/js/fontawesome.all.min.js"></script>
34+
<script src="./static/js/bulma-carousel.min.js"></script>
35+
<script src="./static/js/bulma-slider.min.js"></script>
36+
<script src="./static/js/index.js"></script>
37+
</head>
38+
39+
<body>
40+
41+
<nav class="navbar" role="navigation" aria-label="main navigation">
42+
<div class="navbar-brand">
43+
<a role="button" class="navbar-burger" aria-label="menu" aria-expanded="false">
44+
<span aria-hidden="true"></span>
45+
<span aria-hidden="true"></span>
46+
<span aria-hidden="true"></span>
47+
</a>
48+
</div>
49+
</nav>
50+
51+
<section class="hero">
52+
<div class="hero-body" style="padding-top: 2em;">
53+
<div class="container is-max-desktop">
54+
<div class="columns is-centered">
55+
<div class="column has-text-centered">
56+
<h1 class="title is-1 publication-title">3DXTalker: An Integrated Framework for Expressive 3D Talking Avatars</h1>
57+
<div class="is-size-3 publication-venue">
58+
59+
</div>
60+
<div class="is-size-5 publication-authors">
61+
<span class="author-block">
62+
Zhongju Wang<sup>1</sup>,</span>
63+
<span class="author-block">
64+
Zhenhong Sun<sup>2</sup>,</span>
65+
<span class="author-block">
66+
Beier Wang<sup>1</sup>,
67+
</span>
68+
<span class="author-block">
69+
Yifu Wang<sup>3</sup>,
70+
</span>
71+
<span class="author-block">
72+
Daoyi Dong<sup>4</sup>,
73+
</span>
74+
<span class="author-block">
75+
Huadong Mo<sup>1</sup>,
76+
</span>
77+
<span class="author-block">
78+
Hongdong Li<sup>2</sup>
79+
</span>
80+
</div>
81+
82+
<div class="is-size-5 publication-authors">
83+
<span class="author-block"><sup>1</sup>University of New South Wales,</span>
84+
<span class="author-block"><sup>2</sup>Australian National University,</span>
85+
<span class="author-block"><sup>3</sup>Vertex Lab,</span>
86+
<span class="author-block"><sup>4</sup>University of Technology Sydney</span>
87+
</div>
88+
89+
<div class="column has-text-centered">
90+
<div class="publication-links">
91+
<!-- PDF Link. -->
92+
<span class="link-block">
93+
<a href="#" class="external-link button is-normal is-rounded is-dark">
94+
<span class="icon">
95+
<i class="ai ai-arxiv"></i>
96+
</span>
97+
<span>arXiv (Coming Soon)</span>
98+
</a>
99+
</span>
100+
<!-- Code Link. -->
101+
<span class="link-block">
102+
<a href="#"
103+
class="external-link button is-normal is-rounded is-dark">
104+
<span class="icon">
105+
<i class="fab fa-github"></i>
106+
</span>
107+
<span>Code (Coming Soon)</span>
108+
</a>
109+
</span>
110+
<!-- <a href="https://github.com/google/nerfies/releases/tag/0.1"
111+
class="external-link button is-normal is-rounded is-dark">
112+
<span class="icon">
113+
<i class="far fa-images"></i>
114+
</span>
115+
<span>Data</span>
116+
</a> -->
117+
</div>
118+
</div>
119+
</div>
120+
</div>
121+
</div>
122+
</div>
123+
</section>
124+
125+
<section class="hero is-light is-small teaser">
126+
<div class="container is-max-desktop">
127+
<div class="hero-body">
128+
<div class="columns is-centered is-multiline">
129+
<div class="column is-full">
130+
<video autoplay muted loop playsinline controls style="width: 100%;">
131+
<source src="./static/videos/demo_A.mp4" type="video/mp4">
132+
Your browser does not support the video tag.
133+
</video>
134+
</div>
135+
<div class="column is-full">
136+
<video autoplay muted loop playsinline controls style="width: 100%;">
137+
<source src="./static/videos/demo_B.mp4" type="video/mp4">
138+
Your browser does not support the video tag.
139+
</video>
140+
</div>
141+
</div>
142+
<div class="content has-text-centered">
143+
<p>
144+
<span class="dnerf">3DXTalker</span> generates identity-consistent, expressive 3D talking avatars from a single reference image and speech audio, achieving accurate lip synchronization, expressive emotion control, and natural head-pose dynamics.
145+
</p>
146+
</div>
147+
</div>
148+
</div>
149+
</section>
150+
151+
<section class="section">
152+
<div class="container is-max-desktop">
153+
<!-- Abstract. -->
154+
<div class="columns is-centered has-text-centered">
155+
<div class="column is-four-fifths">
156+
<h2 class="title is-3">Abstract</h2>
157+
<div class="content has-text-justified">
158+
<p>
159+
Audio-driven 3D talking avatar generation is increasingly important in virtual communication, digital humans, and interactive media, where avatars must preserve identity, synchronize lip motion with speech, express emotion, and exhibit lifelike spatial dynamics, collectively defining a broader objective of <i>expressivity</i>. However, achieving this remains challenging due to insufficient training data with limited subject identities, narrow audio representations, and restricted explicit controllability. In this paper, we propose 3DXTalker, an expressive 3D talking avatar through data-curated identity modeling, audio-rich representations, and spatial dynamics controllability. 3DXTalker enables scalable identity modeling via 2D-to-3D data curation pipeline and disentangled representations, alleviating data scarcity and improving identity generalization. Then, we introduce frame-wise amplitude and emotional cues beyond standard speech embeddings, ensuring superior lip synchronization and nuanced expression modulation. These cues are unified by a flow-matching-based transformer for coherent facial dynamics. Moreover, 3DXTalker also enables natural head-pose motion generation while supporting stylized control via prompt-based conditioning. Extensive experiments show that 3DXTalker integrates lip synchronization, emotional expression, and head-pose dynamics within a unified framework, achieves superior performance in 3D talking avatar generation.
160+
</p>
161+
</div>
162+
</div>
163+
</div>
164+
<!--/ Abstract. -->
165+
166+
<!-- Method. -->
167+
<div class="columns is-centered has-text-centered">
168+
<div class="column is-four-fifths">
169+
<h2 class="title is-3">Method</h2>
170+
<img src="./static/images/xtalker3D.png" alt="3DXTalker pipeline">
171+
<h2 class="subtitle has-text-centered">Overview of the 3DXTalker framework.</h2>
172+
</div>
173+
</div>
174+
<!--/ Method. -->
175+
176+
<!-- Emotion Control -->
177+
<div class="columns is-centered has-text-centered">
178+
<div class="column is-four-fifths">
179+
<h2 class="title is-3">Emotion Control</h2>
180+
<div class="columns is-centered is-multiline">
181+
<div class="column is-one-third">
182+
<video autoplay muted loop playsinline controls style="width: 100%;">
183+
<source src="./static/videos/C_Emotion/3DXTalker_happy.mp4" type="video/mp4">
184+
</video>
185+
<p class="has-text-centered"><strong>Happy</strong></p>
186+
</div>
187+
<div class="column is-one-third">
188+
<video autoplay muted loop playsinline controls style="width: 100%;">
189+
<source src="./static/videos/C_Emotion/3DXTalker_sad.mp4" type="video/mp4">
190+
</video>
191+
<p class="has-text-centered"><strong>Sad</strong></p>
192+
</div>
193+
<div class="column is-one-third">
194+
<video autoplay muted loop playsinline controls style="width: 100%;">
195+
<source src="./static/videos/C_Emotion/3DXTalker_angry.mp4" type="video/mp4">
196+
</video>
197+
<p class="has-text-centered"><strong>Angry</strong></p>
198+
</div>
199+
</div>
200+
</div>
201+
</div>
202+
<!--/ Emotion Control -->
203+
204+
<!-- Head Pose -->
205+
<div class="columns is-centered has-text-centered">
206+
<div class="column is-four-fifths">
207+
<h2 class="title is-3">Head Pose Control</h2>
208+
<video autoplay muted loop playsinline controls style="width: 100%;">
209+
<source src="./static/videos/D_HeadPose/3DXTalker_HeadPose.mp4" type="video/mp4">
210+
</video>
211+
</div>
212+
</div>
213+
<!--/ Head Pose -->
214+
215+
<!-- Camera Movements -->
216+
<div class="columns is-centered has-text-centered">
217+
<div class="column is-four-fifths">
218+
<h2 class="title is-3">Camera Movements</h2>
219+
<video autoplay muted loop playsinline controls style="width: 100%;">
220+
<source src="./static/videos/E_CameraMovements/3DXTalker_CameraMovements.mp4" type="video/mp4">
221+
</video>
222+
</div>
223+
</div>
224+
<!--/ Camera Movements -->
225+
226+
<!-- Wan Render -->
227+
<div class="columns is-centered has-text-centered">
228+
<div class="column is-four-fifths">
229+
<h2 class="title is-3">Downstream Application</h2>
230+
<div class="columns is-centered is-multiline">
231+
<div class="column is-full">
232+
<video autoplay muted loop playsinline controls style="width: 100%;">
233+
<source src="./static/videos/G_WanRender/G1.mp4" type="video/mp4">
234+
</video>
235+
</div>
236+
<div class="column is-full">
237+
<video autoplay muted loop playsinline controls style="width: 100%;">
238+
<source src="./static/videos/G_WanRender/G2.mp4" type="video/mp4">
239+
</video>
240+
</div>
241+
</div>
242+
</div>
243+
</div>
244+
<!--/ Wan Render -->
245+
</div>
246+
</section>
247+
248+
<!-- Uncomment when video is available
249+
<section class="hero is-light is-small">
250+
<div class="container is-max-desktop" style="width: 100%;">
251+
<div class="hero-body">
252+
<div class="columns is-centered has-text-centered">
253+
<div class="column is-four-fifths">
254+
<h2 class="title is-3">Video</h2>
255+
<div class="publication-video">
256+
<iframe src="https://www.youtube.com/embed/YOUR_VIDEO_ID" frameborder="0"
257+
allow="autoplay; encrypted-media" allowfullscreen></iframe>
258+
</div>
259+
</div>
260+
</div>
261+
</div>
262+
</div>
263+
</section>
264+
-->
265+
266+
<section class="section" id="BibTeX">
267+
<div class="container is-max-desktop content">
268+
<h2 class="title">BibTeX</h2>
269+
<pre><code>@article{wang20243dxtalker,
270+
title={3DXTalker: An Integrated Framework for Expressive 3D Talking Avatars},
271+
author={Wang, Zhongju and Sun, Zhenhong and Wang, Beier and Wang, Yifu and Dong, Daoyi and Mo, Huadong and Li, Hongdong},
272+
journal={arXiv preprint},
273+
year={2026}
274+
}</code></pre>
275+
</div>
276+
</section>
277+
278+
<footer class="footer">
279+
<div class="container">
280+
<!-- <div class="content has-text-centered">
281+
<a class="icon-link" href="./static/videos/nerfies_paper.pdf">
282+
<i class="fas fa-file-pdf"></i>
283+
</a>
284+
<a class="icon-link" href="https://github.com/keunhong" class="external-link" disabled>
285+
<i class="fab fa-github"></i>
286+
</a>
287+
</div> -->
288+
<div class="columns is-centered">
289+
<div class="column is-8">
290+
<div class="content">
291+
<p>
292+
This website is licensed under a <a rel="license"
293+
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
294+
Commons Attribution-ShareAlike 4.0 International License</a>.
295+
</p>
296+
</div>
297+
</div>
298+
</div>
299+
</div>
300+
</footer>
301+
302+
</body>
303+
304+
</html>

‎static/css/bulma-carousel.min.css‎

Lines changed: 1 addition & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

0 commit comments

Comments
 (0)