-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathindex.html
1063 lines (990 loc) · 44 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
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<meta name="description"
content=" Sparse Semantic Supervised Tensorial Radiance Field (3S-TensoRF)">
<meta name="keywords" content="Semanrtic NeRF, 3S-TensoRF, NeRF">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Multi-scale Distilled Feature Field with VM Factorized Convolution for Sparse-view Supervised 3D-consistent Panoptic Segmentation</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>
<script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=AM_HTMLorMML-full"></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/model_title.png">
<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>
<script src="./static/js/app.js"></script>
<script src="./static/js/video_comparison.js"></script>
<link rel="stylesheet" href="./static/css/dics.original.css">
<script src="./static/js/event_handler.js"></script>
<script src="./static/js/dics.original.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://keunhong.com">
<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">
HyperNeRF
</a>
<a class="navbar-item" href="https://nerfies.github.io">
Nerfies
</a>
<a class="navbar-item" href="https://latentfusion.github.io">
LatentFusion
</a>
<a class="navbar-item" href="https://photoshape.github.io">
PhotoShape
</a>
</div>
</div>
</div>
</div>
</nav> -->
<section class="hero">
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered is-fullwidth">
<div class="column has-text-centered is-full ">
<h1 class="title is-3 publication-title">Multi-scale Distilled Feature Field with VM Factorized Convolution for Sparse-view Supervised 3D-consistent Panoptic Segmentation</h1>
<div class="is-size-5 publication-authors">
<span class="author-block">
Bin Dou<sup>1</sup>,</span>
<span class="author-block">
Yongjia Ma<sup>1</sup>,</span>
<span class="author-block">
Tianyu Zhang<sup>1</sup>,
</span>
<span class="author-block">
Zejian Yuan<sup>1</sup>
</span>
<!-- <span class="author-block">
<a href="https://www.danbgoldman.com">Dan B Goldman</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://homes.cs.washington.edu/~seitz/">Steven M. Seitz</a><sup>1,2</sup>,
</span>
<span class="author-block">
<a href="http://www.ricardomartinbrualla.com">Ricardo Martin-Brualla</a><sup>2</sup>
</span><! -->
</div>
<div class="is-size-5 publication-authors">
<span class="author-block"><sup>1</sup>Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University</span>
<!-- <span class="author-block"><sup>2</sup>Google Research</span> -->
</div>
<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<!-- <span class="link-block">
<a href
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
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> -->
<!-- Video Link. -->
<!-- <span class="link-block">
<a href
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-youtube"></i>
</span>
<span>Video</span>
</a>
</span> -->
<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/David-Dou/MDP-TensoRSF"
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://github.com/google/nerfies/releases/tag/0.1"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="far fa-images"></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">
<div class="columns is-centered has-text-centered">
<div class="column is-full-width">
<div class="b-dics" style="width: 600px; font-weight: 600;">
<img src="static/videos/gt_test.gif" alt="RGB">
<img src="static/videos/ours_test.gif" alt="Sparse-view Supervised Panoptic Segmentation">
</div>
</div>
</div>
</div>
</div>
</section>
<!-- overview video -->
<!-- <section class="hero teaser">
<div class="container is-max-desktop">
<div class="hero-body">
<video id="teaser" autoplay muted loop playsinline height="100%">
<source src="./static/videos/sem.mp4"
type="video/mp4">
</video>
<h2 class="subtitle has-text-centered">
</span> Overview video
</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 is-multiline">
<div class="column is-four-fifths">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
We propose Multi-scale Distilled & Postprocessed Tensorial Raw-Semantic Field(MDP-TensoRSF),
a method for 3D-consistent panoptic segmentation under sparse-view supervision.
Previous 3D segmentation methods have relied on dense-view labels as they suffer from a performance decline
which is particularly shape when extremely sparser-view labels are provided and fail to give satisfactory segmentation results
with few number of supervisory viewpoints. Existing image-based distillation provides reasonable solution for the few-shot problem,
however, features extracted by pre-trained teacher networks, such as DINO, will be sensitive to specular highlight regions in RGB images
and lead to missegmentation for complex scenes. Our method achieves reliable 3D-consistent panoptic segmentation without dense-view labels,
by distilling multi-scale raw-semantic knowledge extracted from images and further postprocessing it with our VM factorized 3D convolution.
Specifically, we present a two-stage learning model. For the first distillation stage,
multi-scale tensorial raw-semantic feature field serves as the student model to distill DINO features,
and for the following segmentation stage,
we enhance its guidance for few-shot panoptic segmentation by convolutional postprocessing,
incorporating our designed 3DConv-VM technique.
Experimental results show that our model can perform high-quality panoptic segmentation under sparse-view supervision,
as our model exhibits less performance degradation with sparser-view labels and outperforms other segmentation models in our sparest setting,
with approximately 12% mIoU, 15%
<math xmlns="http://www.w3.org/1998/Math/MathML">
<msup>
<mrow>
<mrow>
<mi mathvariant="normal">m</mi>
<mi mathvariant="normal">A</mi>
<mi mathvariant="normal">P</mi>
</mrow>
</mrow>
<mrow>
<mn>0.50</mn>
</mrow>
</msup>
</math>
and 10%
<math xmlns="http://www.w3.org/1998/Math/MathML">
<msup>
<mrow>
<mi mathvariant="normal">P</mi>
<mi mathvariant="normal">Q</mi>
</mrow>
<mrow>
<mrow>
<mi mathvariant="normal">s</mi>
<mi mathvariant="normal">c</mi>
<mi mathvariant="normal">e</mi>
<mi mathvariant="normal">n</mi>
<mi mathvariant="normal">e</mi>
</mrow>
</mrow>
</msup>
</math>
improvement.
</p>
</div>
</div>
</div>
<!--/ Abstract. -->
<!-- Abstract. -->
<div class="columns is-centered has-text-centered is-multiline">
<div class="column is-four-fifths ">
<h2 class="title is-3">Methods</h2>
<div class="content has-text-justified">
<p>
Given posed RGB images
<math xmlns="http://www.w3.org/1998/Math/MathML">
<mo fence="false" stretchy="false">{</mo>
<mi>I</mi>
<mo fence="false" stretchy="false">}</mo>
</math>
of a scene with part of corresponding segmentation annotations <math xmlns="http://www.w3.org/1998/Math/MathML">
<mo fence="false" stretchy="false">{</mo>
<mi>S</mi>
<mo fence="false" stretchy="false">}</mo>
</math>, we aim to build a
scene representational model to achieve 3D-consistent novel-view panoptic segmentation, while using supervisory labels
from as few viewpoints as possible.
The below figure provides an overview of our model's architecture, which mainly
consists of two parts: tensorial scene representation(focusing
on multi-scale knowledge distillation as segmentation prior)
and implicit segmentation field(for postprocessing distilled features and mapping them to panoptic segmentation).
</p>
</div>
</div>
<p>
<!-- <img src="./static/images/model.png"
class="interpolation-image"
alt="Interpolate start reference image."/> -->
<figure class="image is-9by6">
<!-- <img src="./static/images/model.svg" alt="Interpolate start reference image."> -->
<img src="./static/images/model.png" alt="Interpolate start reference image.">
</figure>
</p>
</div>
<br/>
<br/>
<!--/Methods -->
<div class="columns is-centered has-text-centered is-multiline">
<h2 class="title is-3">Comparisons</h2>
<div class="column is-four-fifths ">
<h3 class="title is-4">Comparison on Performance-Sparsity Trend</h3>
<div class="content has-text-justified">
<p>
<!-- Comparison on performance-sparsity trend. -->
Each line chart takes Sparsity Ratio of supervisory labels as the independent variable,
and different model's metrics value calculated by
averaging panoptic segmentation metrics over all scenes from (a)Replica/(b)ScanNet dataset
as the implicit variable.
</p>
</div>
</div>
<p>
<figure class="image is-9by6">
<img src="./static/images/demo.svg" alt="Interpolate start reference image.">
</figure>
</p>
<br/>
<div class="column is-four-fifths ">
<h3 class="title is-4">Comparison under Sparsest-view Supervision</h3>
<div class="content has-text-justified">
<p>
Comparison on novel-view panoptic segmentation performance under sparsest-view supervision
(95% Sparsity Ratio).
</p>
</div>
</div>
<p>
<figure class="image is-9by6">
<img src="./static/images/table.png" alt="Interpolate start reference image.">
</figure>
</p>
</div>
<!-- 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">
<div class="container is-max-desktop">
<!-- Animation. -->
<div class="columns is-centered">
<div class="column is-full-width">
<h2 class="title is-3">Animation</h2>
<!-- Interpolating. -->
<h3 class="title is-4">Rendered Segmentation Maps</h3>
<div class="content has-text-justified">
<p>
Use the slider to observe rendered panoptic segmentation maps from various viewpoints of different methods,
with training labels at 95% Sparsity Ratio.
</p>
</div>
<!-- <div class="column is-vcentered interpolation-panel is-multiline">
<div class="columns is-centered ">
<div class="column is-3 is-offset-0 ">
<div id="GT-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">Ground Truth</p>
</div>
</div>
<div class="column interpolation-video-column">
<div id="interpolation-image-wrapper">
Loading...
</div>
<div class="columns is-centered is-multiline">
<div class="column is-one-fifth">
<p class="has-text-centered has-text-weight-bold is-size-5">SAM</p>
</div>
<div class="column is-one-fifth">
<p class="has-text-centered has-text-weight-bold is-size-5">Semantic-NeRF</p>
</div>
<div class="column is-one-fifth">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-one-fifth">
<p class="has-text-centered has-text-weight-bold is-size-5">Object-SDF</p>
</div>
<div class="column is-one-fifth">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours</p>
</div>
<div class="column is-1">
</div>
</div>
<input class="slider is-full-width is-large is-info"
id="interpolation-slider"
step="1" min="0" max="100" value="0" type="range">
</div>
<div class="column is-3 has-text-centered"> -->
<!-- <img src="./static/images/interpolate_end.jpg"
class="interpolation-image"
alt="Interpolation end reference image."/>
<p class="is-bold">End Frame</p> -->
<!-- </div> -->
<!-- </div> -->
<br/>
<!--/ Interpolating. -->
<div class="columns is-vcentered interpolation-panel ">
<div class="column is-one-quarter ">
<div id="GT-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">Ground Truth</p>
</div>
<div class="column is-three-quarter is-multiline">
<div class="columns ">
<div class="column is-one-third is-offset-0 ">
<div id="MaskDINO-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">MaskDINO</p>
</div>
<div class="column is-one-third is-offset-0 ">
<div id="TensoRF_LP-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">TensoRF+LP</p>
</div>
<div class="column is-one-third is-offset-0 ">
<div id="Semantic-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">Semantic-NeRF</p>
</div>
</div>
<div class="columns ">
<div class="column is-one-third is-offset-0 ">
<div id="DM-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-one-third is-offset-0 ">
<div id="Panoptic-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5">Panoptic-Lifting</p>
</div>
<div class="column is-one-third is-offset-0 ">
<div id="Ours-image-wrapper">
Loading...
</div>
<p class="has-text-centered has-text-weight-bold is-size-5" style="color: rgb(255,0,0)"> Ours </p>
</div>
</div>
<input class="slider is-full-width is-large is-info"
id="interpolation-slider"
step="1" min="0" max="180" value="0" type="range">
</div>
</div>
<!-- Re-rendering. -->
<h3 class="title is-4">Scene Manipulation</h3>
<div class="content has-text-justified">
<p>
Scene manipulation and further inpainted results are provided
as an application of our method.
When compared to DM-NeRF, our segmentation method proves to be
a more reliable foundation for downstream tasks.
<!-- Scene manipulation and additional inpainted outcomes demonstrate the practical application of our approach. -->
<!-- When compared to DM-NeRF, our segmentation method proves to be a more dependable foundation for subsequent tasks. -->
<!-- We can also animate the scene of editing and inpainting .
Use the slider here to see the editing results. -->
</p>
</div>
<h4 class="title is-5">Translating</h4>
<div class="column is-multiline is-vcentered interpolation-panel ">
<div class="columns is-vcentered interpolation-panel ">
<!-- <div class="column is-3 has-text-centered">
<img src="./static/editing/gt.png"
alt="GT-image"
class="image "/>
<p class="is-size-5 has-text-centered has-text-weight-bold">Before Manipulation</p>
</div> -->
<!-- <div class="column is-3 has-text-centered">
<p class="is-size-5 has-text-centered has-text-weight-bold ">DM-NeRF</p>
<div id="Editing-image2-wrapper">
Loading...
</div>
</div> -->
<!-- <div class="column is-8 has-text-centered ">
<div id="Editing-image1-wrapper">
Loading...
</div>
<div class="columns is-centered ">
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Translated)</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Inpainted)</p>
</div>
</div>
<p>
<input class="slider is-full-width is-large is-info"
id="Editing-slider"
step="1" min="0" max="4" value="0" type="range">
</p>
</div> -->
<!-- <div class="column is-3 has-text-centered">
<p class="is-size-5 has-text-centered has-text-weight-bold ">DM-NeRF</p>
<div id="Editing-image2-wrapper">
Loading...
</div>
</div> -->
<div class="column is-12 has-text-centered ">
<div id="Editing-image1-wrapper">
Loading...
</div>
<div class="columns is-centered ">
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Before Manipulation</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Translated)</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Inpainted)</p>
</div>
</div>
<p>
<!-- <input class="slider is-full-width is-large is-info"
id="Editing-slider"
step="1" min="0" max="4" value="0" type="range"> -->
<input class="slider is-full-width is-large is-info"
id="Editing-slider"
step="1" min="0" max="3" value="0" type="range">
</p>
</div>
</div>
</div>
<!-- <h4 class="title is-5">room0</h4>
<div class="column is-multiline is-vcentered interpolation-panel ">
<div class="columns is-vcentered interpolation-panel ">
<div class="column is-3 has-text-centered">
<img src="./static/editing/gt_room0.png"
alt="GT-image"
class="image "/>
<p class="is-size-5 has-text-centered has-text-weight-bold">Before Manipulation</p>
</div>
<div class="column is-8 has-text-centered ">
<div id="Editing-image2-wrapper">
Loading...
</div>
<div class="columns is-centered ">
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Edit)</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Inpaint)</p>
</div>
</div>
<p>
<input class="slider is-full-width is-large is-info"
id="Editing-slider1"
step="1" min="0" max="4" value="0" type="range">
</p>
</div>
</div>
</div> -->
<br/>
<h4 class="title is-5">Erasing</h4>
<!-- <div class="content has-text-justified ">
<p>
We can also animate the scene of erasing the object .Use the button here to see the erasing results.
</p>
</div>
<h4 class="title is-5">office3</h4> -->
<div class="columns is-vcentered interpolation-panel">
<!-- <button id="change-image-btn" class="button ">Inpainting</button> -->
<!-- <div class="column is-3 has-text-centered "> -->
<!-- <img src="./static/editing/38_rgb_gt.png"
alt="GT-image"
class="image is-512x512"/> -->
<!-- <img src="./static/editing/38_rgb_gt_new.png"
alt="GT-image"
class="image is-648x648"/>
<p class="is-size-5 has-text-centered has-text-weight-bold">Before Manipulation</p>
</div>
<div class="column is-8 has-text-centered">
<img id = "output-img1"
src="./static/editing/erasing_gt.png"
alt="Erasing-image"
class="image is-648x648"/>
<div class="columns is-centered ">
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Manipulated)</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Inpainted)</p>
</div>
</div>
<button id="change-image-btn1" class="button is-medium is-info has-text-weight-bold">Erasing</button>
</div> -->
<div class="column is-12 has-text-centered">
<img id = "output-img1"
src="./static/editing/before_erasing_office3.png"
alt="Erasing-image"
class="image is-648x648"/>
<div class="columns is-centered">
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Before Manipulation</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Erased)</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Inpainted)</p>
</div>
</div>
<div class="columns is-centered">
<div class="column is-3">
<button id="change-image-btn1" class="button is-medium is-info has-text-weight-bold">Erasing</button>
</div>
<div class="column is-3">
<button id="reset-image-btn1" class="button is-medium is-info has-text-weight-bold">Reset</button>
</div>
</div>
<!-- <button id="change-image-btn1" class="button is-medium is-info has-text-weight-bold">Erasing</button>
<button id="reset-image-btn1" class="button is-medium is-info has-text-weight-bold">Reset</button> -->
</div>
<!-- <div class="content has-text-justified is-multiline">
<div class="column is-narrow">
<p class="is-size-4 has-text-centered has-text-weight-bold">Erasing</p>
</div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column is-narrow"></div>
<div class="column">
<p class="is-size-4 has-text-centered has-text-weight-bold">Inpainting</p>
</div>
</div> -->
</div>
<!-- <h4 class="title is-5">room0</h4> -->
<div class="columns is-vcentered interpolation-panel">
<!-- <div class="column is-3 has-text-centered "> -->
<!-- <img src="./static/editing/7_rgb_gt.png"
alt="GT-image"
class="image is-512x512"/> -->
<!-- <img src="./static/editing/7_rgb_gt_new.png"
alt="GT-image"
class="image is-512x512"/>
<p class="is-size-5 has-text-centered has-text-weight-bold">Before Manipulation</p>
</div>
<div class="column is-8 has-text-centered">
<img id = "output-img2"
src="./static/editing/erasing_gt_room0.png"
alt="Erasing-image"
class="image is-648x648"/>
<div class="columns is-centered ">
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Manipulated)</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours(Inpainted)</p>
</div>
</div>
<button id="change-image-btn2" class="button is-medium is-info has-text-weight-bold">Erasing</button>
</div> -->
<div class="column is-12 has-text-centered">
<img id = "output-img2"
src="./static/editing/before_erasing_room0.png"
alt="Erasing-image"
class="image is-648x648"/>
<div class="columns is-centered">
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Before Manipulation</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">DM-NeRF</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Erased)</p>
</div>
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Ours (Inpainted)</p>
</div>
</div>
<div class="columns is-centered">
<div class="column is-3">
<button id="change-image-btn2" class="button is-medium is-info has-text-weight-bold">Erasing</button>
</div>
<div class="column is-3">
<button id="reset-image-btn2" class="button is-medium is-info has-text-weight-bold">Reset</button>
</div>
</div>
</div>
</div>
<h3 class="title is-4">DINO Features</h3>
<div class="content has-text-justified">
<p>
We visualize rendered DINO feature maps from distilled feature fields.
<!-- Scenes are from Replica and ScanNet. -->
</p>
</div>
<!--/ DINO. -->
<div class="columns is-vcentered ">
<!-- <button id="change-image-btn" class="button ">Impainting</button> -->
<div class="column is-6 has-text-centered ">
<img src="./static/dino/Replica.jpg"
alt="DINO-image"
class="image is-512x512"/>
<div class="columns is-centered is-multiline">
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">Replica</p>
</div>
</div>
</div>
<div class="column is-6 has-text-centered ">
<img src="./static/dino/ScanNet.jpg"
alt="DINO-image"
class="image is-512x512"/>
<div class="columns is-centered is-multiline">
<div class="column is-3">
<p class="has-text-centered has-text-weight-bold is-size-5">ScanNet</p>
</div>
</div>
</div>
</div>
<!-- dino-VIDOE -->
<!-- <h3 class="title is-4">DINO Video</h3>
<div class="content has-text-justified">
<p>
We visualize feature fields distilled from DINO.
</p>
</div>
<div class="columns is-centered">
<div class="column is-3">
<h5 class="title is-6 is-center">Replica-office_0</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/office0_rgb.mp4" type="video/mp4">
</video>
</div>
</div>
/ Visual Effects. -->
<!-- Matting. -->
<!-- <div class="column is-3">
<h5 class="title is-6 is-center">(Dino field)</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/office0_dino.mp4" type="video/mp4">
</video>
</div>
</div>
<div class="column is-3">
<h5 class="title is-6 is-center">Replica-office_2</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/office2_rgb.mp4" type="video/mp4">
</video>
</div>
</div>
<div class="column is-3">
<h5 class="title is-6 is-center">(Dino field)</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/office2_dino.mp4" type="video/mp4">
</video>
</div>
</div>
</div> -->
<!-- <div class="columns is-centered">
<div class="column is-3">
<h5 class="title is-6 is-center">Scene0010</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/scene0010_rgb.mp4" type="video/mp4">
</video>
</div>
</div>
<!--/ Visual Effects. -->
<!-- Matting. -->
<!-- <div class="column is-3">
<h5 class="title is-6 is-center">(Dino field)</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/scene0010_dino.mp4" type="video/mp4">
</video>
</div>
</div>
<div class="column is-3">
<h5 class="title is-6 is-center">Scene0038</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/scene0038_rgb.mp4" type="video/mp4">
</video>
</div>
</div>
<div class="column is-3">
<h5 class="title is-6 is-center">(Dino field)</h5>
<div class="content">
<video width="320" height="240" autoplay muted loop playsinline height="70%">
<source src="./static/dino/scene0038_dino.mp4" type="video/mp4">
</video>
</div>
</div>
</div> -->
</div>
</div>
<!--/ Animation. -->
<h3 class="title is-4">Mesh Reconstruction Results</h3>
<div class="content has-text-justified">
<p>
Mesh results are visualized to show the geometric reconstruction improvement
of our VM factorized SDF field rather than previous σ field.
</p>
</div>
<div class="column is-vcentered interpolation-panel ">
<div class="column interpolation-video-column">
<div class="columns interpolation-video-column is-multiline">
<div class="column is-4 ">
<div id="Mesh1-image-wrapper">
Loading...
</div>
</div>
<div class="column is-4 ">
<div id="Mesh2-image-wrapper">
Loading...
</div>
</div>
<div class="column is-4 ">
<div id="Mesh3-image-wrapper">
Loading...
</div>
</div>
</div>
<div class="columns is-centered is-multiline">
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">Ground Truth</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">w/o SDF</p>
</div>
<div class="column is-4">
<p class="has-text-centered has-text-weight-bold is-size-5">w/ SDF</p>
</div>
</div>
<input class="slider is-full-width is-large is-info"
id="Mesh-slider"
step="1" min="0" max="30" value="0" type="range">
</div>
<!-- <div class="column is-3 has-text-centered"> -->
<!-- <img src="./static/images/interpolate_end.jpg"
class="interpolation-image"
alt="Interpolation end reference image."/>
<p class="is-bold">End Frame</p> -->
<!-- </div> -->
</div>
<br>
<!-- Concurrent Work. -->
<div class="columns is-centered">