-
Notifications
You must be signed in to change notification settings - Fork 0
/
index.html
894 lines (831 loc) · 39.4 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
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="keywords" content="OpenSun3D">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Open☀️3D </title>
<!-- <link href="https://fonts.googleapis.com/css?family=Nunito|Google+Sans|Noto+Sans|Castoro" rel="stylesheet"> -->
<link rel="stylesheet" href="./static/css/bulma.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">
<link rel="stylesheet" href="css/style.css"> <!-- Resource style -->
<script src="js/modernizr.js"></script> <!-- Modernizr -->
<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>
<style>
.rcorners1 {
border-radius: 10px;
background: #ffffffd0;
padding: 5px;
font-size: 120%;
color: #5c5c5c;
}
.button {
border-radius: 10px;
background: #ffffffd0;
padding: 5px 15px 5px 15px;
}
.dropdown {
position: relative;
display: inline-block;
}
.dropdown-content {
display: none;
position: absolute;
/* background-color: #f9f9f9; */
min-width: 140px;
box-shadow: 0px 8px 16px 0px rgba(0, 0, 0, 0.2);
padding: 5px 15px 5px 15px;
z-index: 1;
text-align: left;
color: black;
}
.dropdown:hover .dropdown-content {
display: block;
font-size: 14px;
}
</style>
</head>
<body>
<section class="hero">
<div class="hero-body" style="background-color: #1C2D59">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title" style="color: white">OpenSUN3D</h1>
<p class="title is-4" style="color: white">3<sup>rd</sup> Workshop on <br>Open-Vocabulary 3D Scene
Understanding</p>
<h1 class="is-is-5" style="color: white">in conjunction with ECCV 2024 in Milan, Italy.</h1>
<b style="color: white">September 29, Sunday 14:00 - 17:30 - Room: Amber 4</b>
<br>
</div>
</div>
</div>
</div>
</section>
<section class="hero teaser" style="margin-top: 25px">
<div class="container is-max-desktop">
<div class="hero-body">
<h2 class="subtitle has-text-centered">
<!-- <a href="#challenge" class="button">Challenge</a> -->
<a href="#schedule" class="button">Schedule</a>
<a href="#speakers" class="button">Speakers</a>
<a href="#papers" class="button">Papers</a>
<a href="#dates" class="button">Dates</a>
<a href="#relatedwork" class="button">Related Work</a>
<a href="#organizers" class="button">Organizers</a>
<div class="dropdown">
<span class="button">All Editions <i class="fa fa-chevron-down" aria-hidden="true"></i></span>
<div class="dropdown-content">
<a href="index.html">ECCV 2024</a>
<a href="index_cvpr24.html">CVPR 2024</a>
<a href="index_iccv23.html">ICCV 2023</a>
</div>
</div>
</h2>
</div>
</div>
</section>
<section class="section" id="Motivation">
<div class="container is-max-desktop content">
<h2 class="title">Introduction</h2>
<div class="content has-text-justified">
The ability to perceive, understand and interact with arbitrary 3D environments is a long-standing goal in
research with applications in AR/VR, health, robotics and so on.
Current 3D scene understanding models are largely limited to low-level recognition tasks such as object
detection or semantic segmentation,
and do not generalize well beyond the a pre-defined set of training labels.
More recently, large visual-language models (VLM), such as CLIP, have demonstrated impressive capabilities
trained
solely on internet-scale image-language pairs.
Some initial works have shown that these models have the potential to extend 3D scene understanding not only
to open set recognition, but also offer additional applications such as affordances, materials, activities,
and properties of unseen environments.
The goal of this workshop is to bundle these efforts and to discuss and establish clear task
definitions, evaluation metrics, and benchmark datasets.
</div>
</div>
</section>
<!-- <section class="section" style="margin-top: -50px">
<div class="container is-max-desktop">
<section class="section" id="Challenge">
<div class="container is-max-desktop content">
<h2 class="title" id="challenge">Challenge 🚀</h2>
This year, our challenge will consist of two tracks, open-vocabulary 3D object instance search and
open-vocabulary 3D functionality grounding.
<br>
<ul>
<li><b>Challenge Track 1</b>: <a href="https://opensun3d.github.io/cvpr24-challenge/track_1">Open-vocabulary
3D Object Instance
Search</a></li>
<ul>
<li><b>Submission Portal</b>: <a
href="https://eval.ai/web/challenges/challenge-page/2102/overview">EvalAI</a></li>
<li><b>Data Instructions & Helper Scripts</b>: April 17, 2024</li>
<li><b>Dev Phase Start</b>: April 17, 2024</li>
<li><b>Submission Portal Start</b>: April 19, 2024</li>
<li><b>Test Phase Start</b>: May 1, 2024</li>
<li><b>Test Phase End</b>: June 14, 2024 (14:00 Pacific Time)</li>
</ul>
<li><b>Challenge Track 2</b>: <a href="https://opensun3d.github.io/cvpr24-challenge/track_2">Open-vocabulary
3D Functionality
Grounding</a></li>
<ul>
<li><b>Submission Portal</b>: <a
href="https://eval.ai/web/challenges/challenge-page/2262/overview">EvalAI</a></li>
<li><b>Data Instructions & Helper Scripts</b>: April 17, 2024</li>
<li><b>Dev Phase Start</b>: April 17, 2024</li>
<li><b>Submission Portal Start</b>: April 19, 2024</li>
<li><b>Test Phase Start</b>: May 4, 2024</li>
<li><b>Test Phase End</b>: June 14, 2024 (14:00 Pacific Time)</li>
</ul>
</ul>
<p>Please check <a href="https://opensun3d.github.io/index_iccv23.html#challengeresults">this page</a>
out
for an overview of last year's challenge results.
We have also published a <a href="https://arxiv.org/abs/2402.15321"> technical report</a> providing an
overview of our ICCV 2023 workshop challenge.</p>
<p>Our workshop challenge is proudly supported by:</p>
<p align="center">
<img src="static/images/matterport.png" width="40%" style="margin: 20px" />
<img src="static/images/nvidia.png" width="40%" style="margin: 20px" />
</p>
</div>
</section>
</div>
</section>
<section class="section" id="Papers">
<div class="container is-max-desktop content">
<h2 class="title" id="dates">Important Dates 🗓️</h2>
<b>Paper Track</b>: We accept novel full 8-page papers for publication in the proceedings, and
either shorter
4-page extended abstracts or 8-page papers of novel or previously published work that will not
be included in
the
proceedings. All submissions have to follow the <a
href="https://cvpr.thecvf.com/Conferences/2024/AuthorGuidelines">CVPR 2024 author
guidelines.</a>
</li>
<ul>
<li><b>Submission Portal</b>: <a href="https://cmt3.research.microsoft.com/OpenSUN3D2024">CMT</a></li>
<li><b>Paper Submission Deadline</b>: April 1, 2024 (23:59 Pacific Time)</li>
<li><b>Notification to Authors</b>: April 9, 2024</li>
<li><b>Camera-ready submission</b>: April 14, 2024</li>
</ul>
</div>
</section> -->
<section class="section" id="schedule">
<div class="container is-max-desktop content">
<h2 class="title">Schedule</h2>
<div class="content has-text-justified">
<table class="table table-striped">
<tr>
<td width="130">14:00 - 14:15</td>
<td style="background-color: #ddadef37">Welcome & Introduction</td>
<!-- <td></td> -->
</tr>
<tr>
<td>14:15 - 14:45</td>
<td style="background-color:#8cd8fb72">Keynote 1 <b>Tim Meinhardt</b> (NVIDIA)</td>
<!-- <td></td> -->
</tr>
<tr>
<td>14:45 - 15:15</td>
<td style="background-color:#8cd8fb72">Keynote 2 <b>Or Litany</b> (Technion)</td>
<!-- <td></td> -->
</tr>
<tr>
<td>15:15 - 15:30</td>
<td style="background-color:#8cd8fb72">Spotlight <b>Mihai Dusmanu</b> (Microsoft)</td>
<!-- <td></td> -->
</tr>
<tr>
<td>15:30 - 16:30</td>
<td style="background-color: #ddadef37">Poster Session & Coffee Break</td>
<!-- <td></td> -->
</tr>
<tr>
<td>16:30 - 17:00</td>
<td style="background-color:#8cd8fb72">Keynote 3 <b>Alex Bewley</b> (Google)</td>
<!-- <td></td> -->
</tr>
<tr>
<td>17:00 - 17:30</td>
<td style="background-color:#8cd8fb72">Keynote 4 <b>Krishna Murthy</b> (Meta)</td>
<!-- <td></td> -->
</tr>
<tr>
<td>16:45 - 17:30</td>
<td style="background-color: #ddadef37">Concluding Remarks</td>
<!-- <td></td> -->
</tr>
</table>
</div>
</div>
</section>
<section class="section" id="Invited Speakers">
<div class="container is-max-desktop content">
<h2 class="title" id="speakers">Keynote Speakers</h2>
<div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded"
src="https://research.nvidia.com/labs/dvl/author/tim-meinhardt/avatar_hue651a305d599228f790a9f846d4f7dbe_607013_270x270_fill_q90_lanczos_center.jpg">
</figure>
</div>
<div class="column">
<a href="https://research.nvidia.com/labs/dvl/author/tim-meinhardt/" target="_blank">
<p class="title is-4">Tim Meinhardt</p>
<p class="subtitle is-6">Research Scientist at NVIDIA</p>
</a>
</div>
</div>
<div class="content">
Tim Meinhardt is a research scientist at the NVIDIA Dynamic Vision and Learning (DVL) group. His work focuses on video and scene understanding, specifically, multi-object tracking and video segmentation. In 2009, his academic journey started with a B.Sc in physics at the Ludwig Maximilian University (LMU) of Munich. After spending a semester abroad at the Boğaziçi University in Istanbul and finishing his Bachelor in 2013, he worked in Berlin and Munich as a software engineer for web development and robotics. He returned to academia in 2014 for a M.Sc. in Computer Science at the LMU of Munich. For his master’s thesis, he joined the Computer Vision & Artificial Intelligence (CVAI) chair at the Technical University of Munich (TUM). Under the supervision of Prof. Dr. Laura Leal-Taixé and as a member of her TUM DVL group, he continued his research as a Ph.D. candidate until 2023.
</div>
</div>
</div>
<br />
<div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded" src="./static/img/or.jpg">
</figure>
</div>
<a href="https://orlitany.github.io" target="_blank">
<div class="column">
<p class="title is-4">Or Litany</p>
<p class="subtitle is-6">Assistant Professor at the Technion and Senior Research Scientist at NVIDIA</p>
</div>
</a>
</div>
<div class="content">
Or Litany is a Senior Research Scientist at NVIDIA and an Assistant Professor at the Technion,
specializing in 3D computer vision and generative AI.
He is honored to be a 2023 Azrieli Faculty Fellow and a Taub Fellow.
Previously, he conducted postdoctoral research at Stanford University under
Prof. Leonidas Guibas, and at FAIR, hosted by Prof. Jitendra Malik.
His PhD is from Tel-Aviv University, advised by Prof. Alex Bronstein.
My B.Sc. in Physics and Mathematics is from the Hebrew University.
</div>
</div>
</div>
<!-- <div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded"
src="https://research.nvidia.com/labs/dvl/author/laura-leal-taixe/avatar_hu9d324797d9944deea25c064286338fca_252890_270x270_fill_q90_lanczos_center.jpg">
</figure>
</div>
<div class="column">
<a href="https://research.nvidia.com/labs/dvl/author/laura-leal-taixe" target="_blank">
<p class="title is-4">Laura Leal-Taixé</p>
<p class="subtitle is-6">Senior Research Manager at NVIDIA</p>
</a>
</div>
</div>
<div class="content">
Dr. Laura Leal-Taixé is a Senior Research Manager at NVIDIA and also an Adjunct Professor at the Technical
University of Munich (TUM),
leading the Dynamic Vision and Learning group. From 2018 until 2022, she was a tenure-track professor at
TUM.
Before that, she spent two years as a postdoctoral researcher at ETH Zurich, Switzerland, and a year as a
senior postdoctoral researcher in the Computer Vision Group
at the Technical University in Munich. She obtained her PhD from the Leibniz University of Hannover in
Germany, spending a year as a visiting scholar at the University
of Michigan, Ann Arbor, USA. She pursued B.Sc. and M.Sc. in Telecommunications Engineering at the Technical
University of Catalonia (UPC) in her native city of Barcelona.
She went to Boston, USA to do her Masters Thesis at Northeastern University with a fellowship from the
Vodafone foundation.
She is a recipient of the Sofja Kovalevskaja Award of 1.65 million euros in 2017, the Google Faculty Award
in 2021, and the ERC Starting Grant in 2022.
</div>
</div>
</div> -->
<!-- <br />
<div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded" src="static/img/georgia.jpg">
</figure>
</div>
<a href="https://pearl-lab.com/people/georgia-chalvatzaki/" target="_blank">
<div class="column">
<p class="title is-4">Georgia Chalvatzaki
</p>
<p class="subtitle is-6">Full Professor at Technical University of Darmstadt</p>
</div>
</a>
</div>
<div class="content">
As of April 2023, Georgia is a Full Professor for Interactive Robot Perception & Learning at the Computer
Science Department of the Technical University of Darmstadt and Hessian.AI. Before that, she was an
Assistant Professor since February 2022, and Independent Research Group Leader from March 2021, after
getting the renowned Emmy Noether Programme (ENP) fund of the German Research Foundation (DFG). This project
was awarded within the ENP Artificial Intelligence call of the DFG. In her research group, PEARL (previously
iROSA), Dr. Chalvatzaki and her team propose new methods at the intersection of machine learning and
classical robotics, taking the research for embodied AI robotic assistants one step further. The research in
PEARL proposes novel methods for combined planning and learning to enable mobile manipulator robots to solve
complex tasks in house-like environments, with the human-in-the-loop of the interaction process.
</div>
</div>
</div> -->
<br />
<div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded" src="https://avatars.githubusercontent.com/u/8096683?v=4">
</figure>
</div>
<a href="https://alex.bewley.ai/about.php" target="_blank">
<div class="column">
<p class="title is-4">Alex Bewley</p>
<p class="subtitle is-6">Researcher at Google DeepMind</p>
</div>
</a>
</div>
<div class="content">
Alex Bewley, a Senior Researcher at Google DeepMind, works at the intersection of computer vision and robotics,
focusing on combining language, 3D scene understanding, and methods that leverage spatial or temporal structure for high-speed agile robotics.
He has explored the use of large datasets in an open vocabulary setting, notably through his work on Scene Graph ViT and Video OWL-ViT.
He also co-authored the award-winning Open X-Embodiment dataset, contributing to the advancement of large-scale robotic learning.
Alex obtained his PhD in robot vision from the Queensland University of Technology in Australia.
His goal is to enable multi-purpose robots that can handle everyday tasks and adapt to new ones described in natural language.
</div>
</div>
</div>
<br />
<div class="card">
<div class="card-content">
<div class="columns is-vcentered">
<div class="column is-one-quarter">
<figure class="image is-128x128">
<img class="is-rounded" src="https://krrish94.github.io/assets/img/prof_pic.png">
</figure>
</div>
<a href="https://krrish94.github.io" target="_blank">
<div class="column">
<p class="title is-4">Krishna Murthy Jatavallabhula
</p>
<p class="subtitle is-6">AI Research Scientist at Meta</p>
</div>
</a>
</div>
<div class="content">
Krishna Murthy Jatavallabhula is a AI research scientist at Meta.
Previously, he was a postdoc at MIT CSAIL with Antonio Torralba and Josh Tenenbaum.
Prior to that, I received my PhD at Universite de Montreal and Mila, advised by Liam Paull.
His research focuses on building world models for robots and other physical agents to enable them
to perceive, reason, and act just as humans are able. My work spans the robotics, computer vision, and machine learning communities.
His work has been recognized with PhD fellowship awards from NVIDIA and Google, and a best-paper award from IEEE RAL.
</div>
</div>
</div>
</div>
</section>
<section class="section" id="papers">
<div class="container is-max-desktop content">
<h2 class="title" id="accepted">Accepted Papers</h2>
The following papers are accepted for poster presentation during the workshop.
<div class="box">
<article class="media">
<div class="media-content">
<div class="content">
<p>
<strong>SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding</strong><br>
Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang, Xuesong Niu, Tengyu Liu, Qing Li, Siyuan Huang
</p>
</div>
<nav class="level is-mobile">
<div class="level-left">
<a class="level-item" aria-label="reply" href="https://arxiv.org/abs/2401.09340"><span class="icon"> <i class="fas fa-file-pdf"></i> </span> Paper</a>
<a class="level-item" aria-label="retweet" href=""><span class="icon"><i class="fas fa-chalkboard-teacher"></i></span>Poster</a>
</div>
</nav>
</div>
</article>
</div>
<div class="box">
<article class="media">
<div class="media-content">
<div class="content">
<p>
<strong>Unifying 3D Vision-Language Understanding via Promptable Queries</strong><br>
Ziyu Zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Baoxiong Jia, Siyuan Huang, Qing Li
</p>
</div>
<nav class="level is-mobile">
<div class="level-left">
<a class="level-item" aria-label="reply" href="https://arxiv.org/abs/2405.11442"><span class="icon"> <i class="fas fa-file-pdf"></i> </span> Paper</a>
<a class="level-item" aria-label="retweet" href=""><span class="icon"><i class="fas fa-chalkboard-teacher"></i></span>Poster</a>
</div>
</nav>
</div>
</article>
</div>
<div class="box">
<article class="media">
<div class="media-content">
<div class="content">
<p>
<strong>OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation</strong><br>
Zhening Huang, Xiaoyang Wu, Xi CHEN, Hengshuang Zhao, Lei Zhu, Joan Lasenby
</p>
</div>
<nav class="level is-mobile">
<div class="level-left">
<a class="level-item" aria-label="reply" href="https://arxiv.org/abs/2309.00616"><span class="icon"> <i class="fas fa-file-pdf"></i> </span> Paper</a>
<a class="level-item" aria-label="retweet" href=""><span class="icon"><i class="fas fa-chalkboard-teacher"></i></span>Poster</a>
</div>
</nav>
</div>
</article>
</div>
<div class="box">
<article class="media">
<div class="media-content">
<div class="content">
<p>
<strong>Task-oriented Sequential Grounding in 3D Scenes</strong><br>
Zhuofan Zhang, Ziyu Zhu, Pengxiang Li, Tengyu Liu, Xiaojian Ma, Yixin Chen, Baoxiong Jia, Siyuan Huang, Qing Li
</p>
</div>
<nav class="level is-mobile">
<div class="level-left">
<a class="level-item" aria-label="reply" href="https://arxiv.org/abs/2408.04034"><span class="icon"> <i class="fas fa-file-pdf"></i> </span> Paper</a>
<a class="level-item" aria-label="retweet" href=""><span class="icon"><i class="fas fa-chalkboard-teacher"></i></span>Poster</a>
</div>
</nav>
</div>
</article>
</div>
<div class="box">
<article class="media">
<div class="media-content">
<div class="content">
<p>
<strong>Space3D-Bench: Spatial 3D Question Answering Benchmark</strong><br>
Emilia Szymanska, Mihai Dusmanu, Mahdi Rad, Marc Pollefeys
</p>
</div>
<nav class="level is-mobile">
<div class="level-left">
<a class="level-item" aria-label="reply" href="https://arxiv.org/abs/2408.16662"><span class="icon"> <i class="fas fa-file-pdf"></i> </span> Paper</a>
<a class="level-item" aria-label="retweet" href=""><span class="icon"><i class="fas fa-chalkboard-teacher"></i></span>Poster</a>
</div>
</nav>
</div>
</article>
</div>
</div>
</section>
<section class="section" id="dates">
<div class="container is-max-desktop content">
<h2 class="title" id="dates">Dates</h2>
<b>Paper Track</b>: We accept novel full 14-page papers for publication in the proceedings, and
either shorter
4-page extended abstracts or 14-page papers of novel or previously published work that will not
be included in
the
proceedings. Full papers should use the <a href="https://eccv.ecva.net/Conferences/2024/SubmissionPolicies">
official ECCV 2024 template</a>.
Extended abstracts are not subject to the ECCV rules, so they can be in any template but, as a rule to not be
considered a publication in terms of double submission policies,
they should be 4 pages in CVPR template format.
</li>
<ul>
<li><b>Submission Portal</b>: <a href="https://cmt3.research.microsoft.com/OpenSUN3DECCV2024">CMT</a></li>
<li><b>Paper Submission Deadline</b>: <s>August 12, 2024</s></li>
<li><b>Notification to Authors</b>: <s>August 19, 2024</s></li>
<li><b>Camera-ready submission</b>: <s>August 25, 2024</s></li>
</ul>
</div>
</section>
<section class="section" id="Related Work">
<div class="container is-max-desktop content">
<h2 class="title" id="relatedwork">Related Works</h2>
Below is a collection of concurrent and related works in the field of open-set 3D scene understanding.
<ul>
<li><a href="https://concept-fusion.github.io/">ConceptFusion: Open-set Multimodal 3D Mapping</a> RSS'23
</li>
<li><a href="https://pengsongyou.github.io/openscene">OpenScene: 3D Scene Understanding with Open
Vocabularies</a> CVPR'23</li>
<li><a href="https://www.lerf.io">LERF: Language Embedded Radiance Fields</a> ICCV'23</li>
<li><a href="https://pfnet-research.github.io/distilled-feature-fields/">Decomposing NeRF for Editing
via Feature Field Distillation</a> NeurIPS'22</li>
<li><a href="https://semantic-abstraction.cs.columbia.edu/">Semantic Abstraction: Open-World 3D Scene
Understanding from 2D Vision-Language Models</a> CoRL'22</li>
<li><a href="https://rozdavid.github.io/scannet200">Language-Grounded Indoor 3D Semantic Segmentation in
the Wild</a> ECCV'22</li>
<li><a href="https://3dlg-hcvc.github.io/multiscan/">MultiScan: Scalable RGBD Scanning for 3D
Environments with Articulated Objects</a> NeurIPS'22</li>
<li><a href="https://github.com/NVlabs/ODISE">ODISE: Open-Vocabulary Panoptic Segmentation with
Text-to-Image Diffusion Models</a> CVPR'23</li>
<li><a href="https://github.com/Kunhao-Liu/3D-OVS">Weakly Supervised 3D Open-Vocabulary Segmentation</a>
NeurIPS'23</li>
<li><a href="https://arxiv.org/abs/2306.02329">Multi-CLIP: Contrastive Vision-Language Pre-training for
Question Answering tasks in 3D Scenes</a></li>
<li><a href="https://openmask3d.github.io">OpenMask3D: Open-Vocabulary 3D Instance Segmentation</a>
NeurIPS'23</li>
<li><a href="https://arxiv.org/abs/2303.04748">CLIP-FO3D: Learning Free Open-world 3D Scene
Representations from 2D Dense CLIP</li>
<li><a href="https://tsagkas.github.io/vl-fields/">VL-Fields: Towards Language-Grounded Neural Implicit
Spatial Representations</a> ICRA'23</li>
<li><a
href="https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_PLA_Language-Driven_Open-Vocabulary_3D_Scene_Understanding_CVPR_2023_paper.pdf">PLA:
Language-Driven Open-Vocabulary 3D Scene Understanding</a> CVPR'23</li>
<li><a href="https://arxiv.org/abs/2304.00962">RegionPLC: Regional Point-Language Contrastive Learning
for Open-World 3D Scene Understanding</a></li>
<li><a href="https://arxiv.org/abs/2309.00616">OpenIns3D: Snap and Lookup for 3D open-vocabulary
Instance Segmentation</a></li>
<li><a href="https://concept-graphs.github.io/assets/pdf/2023-ConceptGraphs.pdf">ConceptGraphs:
Open-Vocabulary 3D Scene Graphs for Perception and Planning</a></li>
<li><a
href="https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Open-Vocabulary_Point-Cloud_Object_Detection_Without_3D_Annotation_CVPR_2023_paper.pdf">Open-Vocabulary
Point-Cloud Object Detection without 3D Annotation</a> CVPR'23</li>
<li><a href="https://github.com/yangcaoai/CoDA_NeurIPS2023">CoDA: Collaborative Novel
Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection</a> NeurIPS'23
<li><a href="https://scenefun3d.github.io">SceneFun3D: Fine-Grained Functionality and Affordance Understanding
in 3D Scenes</a> CVPR'24
</li>
<br>
</ul>
and many more ... Please
feel free to reach out to add your own work (<a href="mailto:francis.engelmann@ai.ethz.ch">francis.engelmann@ai.ethz.ch</a>).
</ul>
</div>
</section>
<section class="section" id="Organizers">
<div class="container is-max-desktop content">
<h2 class="title" id="organizers">Organizers</h2>
<div class="columns is-centered is-variable is-0">
<div class="column is-one-quarter">
<a href="http://francisengelmann.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/francis.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Francis Engelmann</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://aycatakmaz.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/ayca.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Ayca Takmaz</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://jonasschult.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="https://jonasschult.github.io/images/profile.jpg"
alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Jonas Schult</p>
<p class="subtitle is-7">RWTH Aachen</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://github.com/elisabettafedele">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/elisabetta.png" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Elisabetta Fedele</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
</div>
<div class="columns is-centered is-variable is-0">
<div class="column is-one-quarter">
<a href="https://alexdelitzas.github.io/">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/alex.jpeg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Alex Delitzas</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://github.com/WaldJohannaU">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/johanna.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Johanna Wald</p>
<p class="subtitle is-7">Google</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://pengsongyou.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/songyou.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Songyou Peng</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://zuriabauer.com">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="https://zuriabauer.com/assets/images/ZBauer.png" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Zuria Bauer</p>
<p class="subtitle is-7">ETH Zurich</p>
</div>
</div>
</div>
</div>
</a>
</div>
</div>
<div class="columns is-centered is-variable is-0">
<div class="column is-one-quarter">
<a href="https://orlitany.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/or.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Or Litany</p>
<p class="subtitle is-7">NVIDIA, Technion</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://paschalidoud.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/despoina.jpeg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Despi Paschalidou</p>
<p class="subtitle is-7">Stanford University</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://federicotombari.github.io">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/federico.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Federico Tombari</p>
<p class="subtitle is-7">TUM, Google</p>
</div>
</div>
</div>
</div>
</a>
</div>
<div class="column is-one-quarter">
<a href="https://people.inf.ethz.ch/marc.pollefeys/">
<div class="card">
<div class="card-image">
<figure class="image">
<img class="is-rounded" src="./static/img/marc.jpg" alt="Placeholder image">
</figure>
</div>
<div class="card-content">
<div class="media">
<div class="media-content" style="overflow-x: unset;">
<p class="title is-7 is-spaced">Marc Pollefeys</p>
<p class="subtitle is-7">ETHZ, Microsoft</p>
</div>
</div>
</div>
</div>
</a>
</div>
</div>
</div>
</section>
<section class="hero">
<div class="hero-body" style="background-color: #1C2D59;">
<!-- <div class="container" style="background-color: #333"> -->
<div class="content" align="center">
<img width="300" src="static/images/eth_logo_kurz_neg.png" />
<p style="color: white">
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>.
<br />
It borrows the source code of <a href="https://github.com/nerfies/nerfies.github.io">this website</a>.
We would like to thank Utkarsh Sinha and Keunhong Park.
</p>
</div>
</div>
</section>
</body>
<script src="js/jquery-2.1.1.js"></script>
<script src="js/jquery.mobile.custom.min.js"></script>
<script src="js/main.js"></script>
</html>