forked from nerfies/nerfies.github.io
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.html
339 lines (311 loc) · 13.6 KB
/
index.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="description"
content="LD-T3D is a Large-scale and Diverse Benchmark for Text-based 3D Model Retrieval.">
<meta name="keywords" content="3D, Dataset, TB3DR">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>LD-T3D: A Large-scale and Diverse Benchmark for Text-based 3D Model Retrieval</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>
<nav class="navbar" role="navigation" aria-label="main navigation">
<div class="navbar-brand">
<a role="button" class="navbar-burger" aria-label="menu" aria-expanded="false">
<span aria-hidden="true"></span>
<span aria-hidden="true"></span>
<span aria-hidden="true"></span>
</a>
</div>
<div class="navbar-menu">
<div class="navbar-start" style="flex-grow: 1; justify-content: center;">
<a class="navbar-item" href="https://yuanze.me">
<span class="icon">
<i class="fas fa-home"></i>
</span>
</a>
<div class="navbar-item has-dropdown is-hoverable">
<a class="navbar-link">
More Research
</a>
<div class="navbar-dropdown">
<a class="navbar-item" href="https://hypernerf.github.io">
Placeholder
</a>
</div>
</div>
</div>
</div>
</nav>
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">LD-T3D: A Large-scale and Diverse Benchmark for Text-based 3D Model Retrieval</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
<a href="https://yuanze.me">Ze Yuan</a><sup>1,2</sup>,
</span>
<span class="author-block">
<a href="https://liujiaheng.github.io">Jiaheng Liu</a><sup>3†</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=5C6zNiIAAAAJ&hl=zh-CN">Xuebo Liu</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="http://smuelpenpen.com">Zhipeng Yu</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=pmRn1oMAAAAJ&hl=zh-CN">Jianhao Li</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://openreview.net/profile?id=~Ke_Xu4">Ke Xu</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://yanpei.me">Yan-Pei Cao</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=Dqjnn0gAAAAJ&hl=zh-CN">Ding Liang</a><sup>1</sup>
</span>
</div>
<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>VAST,</span>
<span class="author-block"><sup>2</sup>Beihang University,</span>
<span class="author-block"><sup>3</sup>Nanjing University</span>
</div>
<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<span class="link-block">
<a href="https://arxiv.org/pdf/xxxx.xxxxx"
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>
<span class="link-block">
<a href="https://arxiv.org/abs/xxxx.xxxxx"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>
<!-- Space Link. -->
<span class="link-block">
<a href="https://huggingface.co/spaces/VAST-AI/LD-T3D"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<img src="./static/images/huggingface_logo.svg" alt="Hugging Face Logo" style="width: 32px; height: 32px;">
</span>
<span>Space</span>
</a>
</span>
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/yuanze1024/LD-T3D"
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>
<!-- Dataset Link. -->
<span class="link-block">
<a href="https://huggingface.co/datasets/VAST-AI/LD-T3D"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fa fa-download"></i>
</span>
<span>Data</span>
</a>
</div>
</div>
</div>
</div>
</div>
</div>
</section>
<section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<img src="./static/images/dataset.pdf" alt="Teaser Image" style="width: 100%;">
<h2 class="subtitle has-text-centered">
<b>LD-T3D</b> consists of 1K sub-datasets, and each sub-dataset contains a textual query and about 100 candidate 3D models, which results in 100K text-to-3D model pairs in total.
</h2>
</div>
</div>
</section>
<!-- <section class="hero is-light is-small">
<div class="hero-body">
<div class="container">
<div id="results-carousel" class="carousel results-carousel">
<div class="item item-steve">
<video poster="" id="steve" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/steve.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-chair-tp">
<video poster="" id="chair-tp" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/chair-tp.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-shiba">
<video poster="" id="shiba" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/shiba.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-fullbody">
<video poster="" id="fullbody" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/fullbody.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-blueshirt">
<video poster="" id="blueshirt" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/blueshirt.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-mask">
<video poster="" id="mask" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/mask.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-coffee">
<video poster="" id="coffee" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/coffee.mp4"
type="video/mp4">
</video>
</div>
<div class="item item-toby">
<video poster="" id="toby" autoplay controls muted loop playsinline height="100%">
<source src="./static/videos/toby2.mp4"
type="video/mp4">
</video>
</div>
</div>
</div>
</div>
</section> -->
<section class="section">
<div class="container is-max-desktop">
<!-- Abstract. -->
<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 advent of cross-modal retrieval has bridged the gap between various modalities of data,
enabling the retrieval of relevant samples from one modality based on input from another modality.
This study addresses the challenges in the burgeoning domain of text-based 3D model retrieval,
spurred by the rapid advancement in 3D technologies and the consequent profusion of 3D objects.
Specifically, we introduce a novel Large-scale and Diverse benchmark for Text-based 3D Model Retrieval,
named <b>LD-T3D</b>, consisting of <b>100,000</b> text-to-3D model pairs, which include <b>89,000</b> distinct 3D models
and 1,000 descriptive text queries. First, the benchmark is crafted to enhance the diversity and high quality
of retrieval datasets by sourcing from the Objaverse collection. Then, we meticulously curate the dataset
by employing rigorous filtering criteria to exclude models with low quality or ambiguity. Besides, we {design}
text queries with various levels of difficulty (easy, medium, and hard) and construct the text-to-3D
model pairs, where extensive human reviews are applied to ensure the high quality of the dataset.
Moreover, we {redesigned} evaluation metrics (e.g., mean Average Precision (mAP), mean normalized Discounted
Cumulative Gain (mNDCG), mean First Tier (mFT), and mean Second Tier (mST)) and evaluate the performance
results of existing state-of-the-art methods on LD-T3D. Overall, we believe this benchmark will facilitate
advancements in retrieval algorithms, and support the growth of applications using 3D object databases.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
<!-- Paper video. -->
<!-- <div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe src="https://www.youtube.com/embed/MrKrnHhk8IA?rel=0&showinfo=0"
frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>
</div>
</div>
</div> -->
<!--/ Paper video. -->
</div>
</section>
<section class="section" id="BibTeX">
<div class="container is-max-desktop content">
<h2 class="title">BibTeX</h2>
<pre><code>@article{yuan2024example,
author = {Ze Yuan and Jiaheng Liu and Xuebo Liu and Zhipeng Yu and Jianhao Li and Ke Xu and Yan-Pei Cao and Ding Liang},
title = {LD-T3D: A Large-scale and Diverse Benchmark for Text-based 3D Model Retrieval},
journal = {arXiv preprint arXiv:xxxx.xxxxx},
year = {2024},
url = {https://arxiv.org/abs/xxxx.xxxxx}
}
}</code></pre>
</div>
</section>
<footer class="footer">
<div class="container">
<div class="content has-text-centered">
<a class="icon-link"
href="https://arxiv.org/pdf/xxxx.xxxxx">
<i class="fas fa-file-pdf"></i>
</a>
<a class="icon-link" href="https://github.com/yuanze1024/LD-T3D" class="external-link" disabled>
<i class="fab fa-github"></i>
</a>
</div>
<div class="columns is-centered">
<div class="column is-8">
<div class="content">
<p>
This website is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
<p>
This means you are free to borrow the <a
href="https://github.com/nerfies/nerfies.github.io">source code</a> of this website,
we just ask that you link back to this page in the footer.
Please remember to remove the analytics code included in the header of the website which
you do not want on your website.
</p>
</div>
</div>
</div>
</div>
</footer>
</body>
</html>