en
0.25
0.5
0.75
1.25
1.5
1.75
2
Scene Chronology
Published on Oct 29, 20142410 Views
We present a new method for taking an urban scene reconstructed from a large Internet photo collection and reasoning about its change in appearance through time. Our method estimates when individual 3
Related categories
Chapter list
Scene Chronology00:00
Model of Dubrovnik from 1,000s of Internet photos00:07
Planet-scale reconstruction00:19
Are we done with 3D modeling?00:28
Times Square May 200900:49
Times Square June 201100:51
Times Square July 201100:54
Times Square August 201100:58
Times Square August 201201:01
Times Square01:05
Goal01:20
What data to use? - 101:42
What data to use? - 201:45
What data to use? - 301:54
What data to use? - 401:59
What data to use? - 502:06
Challenges - 102:10
Challenges - 202:15
Challenges - 302:26
Related Work - 103:07
Related Work - 203:25
Contributions03:36
Outline03:55
Possible 4D Representations - 104:04
Possible 4D Representations - 204:26
Possible 4D Representations - 304:34
Approach - 104:53
Approach - 204:56
Approach - 305:02
Approach - 405:13
Approach - 505:29
Approach - 605:33
Approach - 705:48
Approach - 805:53
Approach - 905:58
Approach - 1006:00
Approach - 1106:03
Approach - 1206:07
Point-based 4D Reconstruction06:16
3D Reconstruction - 106:20
3D Reconstruction - 206:24
3D Reconstruction - 306:28
When did a point exist? - 106:41
When did a point exist? - 206:57
When did a point exist? - 307:02
When did a point exist? - 407:07
When did a point exist? - 507:12
Interval Estimation - 107:16
Interval Estimation - 207:24
Interval Estimation - 307:27
Interval Estimation - 407:35
Interval Estimation - 507:39
Interval Estimation - 607:45
Interval Estimation - 708:00
Interval Estimation - 808:06
Negative Observations - 108:15
Negative Observations - 208:20
Negative Observations - 308:23
Negative Observations - 408:29
Negative Observations - 508:31
Negative Observations - 608:34
Point-Based Visualization - 108:49
Spatio-Temporal 4D Segmentation - 108:55
Spatio-Temporal 4D Segmentation - 209:08
Spatio-Temporal Graph09:13
RANSAC Segmentation09:23
Results09:49
Times Square - Manhattan, NYC - 109:53
Times Square - Manhattan, NYC - 210:07
Akihabara - Tokyo - 110:26
Akihabara - Tokyo - 210:30
5Pointz - Queens, NYC - 110:53
5Pointz - Queens, NYC - 211:06
5Pointz - Queens, NYC - 311:32
5Pointz - Queens, NYC - 411:55
Discovered Space-Time Elements12:03
Timestamp Prediction - 112:14
Timestamp Prediction - 212:24
Timestamp Prediction - 312:28
Timestamp Prediction - 412:38
Timestamp Prediction - 512:54
Timestamp Prediction - 613:06
Timestamp Prediction - 713:13
Timestamp Prediction - 813:20
Timestamp Prediction - 913:23
Timestamp Prediction - 1013:26
Limitations13:33
Conclusion13:59
Acknowledgements14:26
Questions?14:31