查看: 984|回复: 6
打印 上一主题 下一主题

[其它] Around the World in 80 Seconds

[复制链接]

797

主题

1

听众

1万

积分

资深设计师

Rank: 7Rank: 7Rank: 7

纳金币
5568
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

跳转到指定楼层
楼主
发表于 2011-12-29 08:56:34 |只看该作者 |倒序浏览
1 Introduction and Related Work

In the famous book “around the world in 80 days” published by

Jules Verne in 1873, two characters aim to perform a world tour

in 80 days. Inspired by Verne’s adventure, we develop a system

to virtually circumnavigate the world in 80 seconds, by collecting

and re-arranging a large collection of Internet images, in a fully

automatic manner, as shown in Figure 1.

Existing methods cannot handle our application. For example,

R. Pergeaux and A. Profit1 need a considerable amount of time

and efforts to manually select and align the pictures. S***cture-

from-motion algorithms (e.g. [Snavely et al. 2006]) can deal with

thousands of images but would require an intractable amount of

processing time and memory for world-scale scenes. In contrast

to scene summarization (e.g. [Simon et al. 2007]), the scene and

the physical locations of the images are changing during the tour.

[Sivic et al. 2008] developed a system to navigate in a set of im-

ages, but it does not take into account geographic data (e.g. Gps

position), temporal data (e.g. acquisition date) or higher-level in-

formation (e.g. objects/buildings present in the pictures or repre-

sentative image selection).

2 Our approach

We automatically collect millions of pictures from Flickr and

grouped the images from the same city into one cluster. A special

sub-cluster “street”, detected by [Oliva and Torralba 2001], is in-

cluded within each city as a connector between landmarks or cities.

Our goal is to build an image sequence with visually smooth transi-

tion. This aim can be transformed into a graph problem which finds

the shortest path from a node in the first cluster to a node in the last

cluster. We define the similarity between two images, I and I

′ by:

d(I; I

′

) = fs(I; I

′

) + cfc(I; I

′

) + vfv(I; I

′

) (1)

where fs measures the s***cture similarity from GIST features

[Oliva and Torralba 2001], fc is the 2 distance between the global

color histograms (i.e. color/tone similarity), fv is the spatial dis-

tance between the vanishing points [Kong et al. 2009], c and v

are the relative weights which are set to 10 and 100 respectively.

Given the shortest path as the skeleton path, the user might want to

adjust the number of images in the sequence while maintaining the

1http://www.youtube.com/watch?v=2N8NaUHR5XI

smooth transition in the image sequence. This can be achieved by

dynamically adding/dropping nodes from the skeleton path based

on the edge weights in real-time.

Our system can also, if desired, automatically find the representa-

tive images within each (sub)cluster. This selection is performed by

[Simon et al. 2007] and will be presented in the Paris tour.

3 Experiments

Figure 1 presents a subset of our result image sequence for

“Jules Verne’s world tour” (world scale). The whole sequence

contains 80 images and constitutes a 80-second world tour

movie. Additional results and video sequences are presented on

http://graphics.ethz.ch/˜jebazin/WT80sec/, es-

pecially a trans-US journey from New-York state to California

(country scale), a tour through the 10 most popular landmarks of

Paris (city scale) and a tour in Ueno Park in Japan along the four

seasons (temporal tour). The whole image sequences were obtained

within a minute, given the similarity graph.

4 Conclusion

In this paper, we have presented an original system that generates,

in a fully automatic manner, a visually smooth image sequence

from Internet images to visualize a traveling tour. Our system al-

lows real-time dynamic adjustment of the number of images pre-

sented in the sequence, interactive path definition by the user and

automatically selects the representative images of landmarks. We

demonstrated our system with tours of various graphical configura-

tions and scales and also extended it to the temporal domain.

References

KONG, H., AUDIBERT, J.-Y., AND PONCE, J. 2009. Vanishing

point detection for road detection. In CVPR’09.

OLIVA, A., AND TORRALBA, A. 2001. Modeling the shape of the

scene: a holistic representation of the spatial envelope. IJCV’01.

SIMON, I., SNAVELY, N., AND SEITZ, S. M. 2007. Scene sum-

marization for online image collections. In ICCV’07.

SIVIC, J., KANEVA, B., TORRALBA, A., AVIDAN, S., AND

FREEMAN, W. T. 2008. Creating and exploring a large photo-

realistic virtual space. In Workshop on Internet Vision (WIV’08).

SNAVELY, N., SEITZ, S. M., AND SZELISKI, R. 2006. Photo

tourism: Exploring photo collections in 3D. In SIGGRAPH’06.
分享到: QQ好友和群QQ好友和群 腾讯微博腾讯微博 腾讯朋友腾讯朋友 微信微信
转播转播0 分享淘帖0 收藏收藏0 支持支持0 反对反对0
回复

使用道具 举报

462

主题

1

听众

31万

积分

首席设计师

Rank: 8Rank: 8

纳金币
2
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

沙发
发表于 2012-4-3 23:26:18 |只看该作者
爱咋咋地!
回复

使用道具 举报

   

671

主题

1

听众

3247

积分

中级设计师

Rank: 5Rank: 5

纳金币
324742
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

板凳
发表于 2012-4-28 23:21:58 |只看该作者
路过、路过、快到鸟,列位请继续...ing
回复

使用道具 举报

   

671

主题

1

听众

3247

积分

中级设计师

Rank: 5Rank: 5

纳金币
324742
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

地板
发表于 2012-7-29 23:27:53 |只看该作者
先垫一块,再说鸟
回复

使用道具 举报

5472

主题

6

听众

1万

积分

版主

Rank: 7Rank: 7Rank: 7

纳金币
76544
精华
23

活跃会员 荣誉管理 突出贡献 优秀版主 论坛元老

5#
发表于 2012-7-30 09:03:05 |只看该作者
3D技术领衔行业应用_技术创新促进产业升级


3D全息投影让乐器也疯狂




2012国际3D魔幻艺术中国特别展杭州揭幕





我国牵头制定智能电视和3D电视国际标准





美国4D影院模拟大风爆炸等效果



什么比Kinect精确100倍?_且看体感控制系统


Unity引擎滑稽3D跑酷玩儿命跑


非同一般的新GPS系统增强现实

回复

使用道具 举报

5969

主题

1

听众

39万

积分

首席设计师

Rank: 8Rank: 8

纳金币
-1
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

6#
发表于 2012-10-24 23:24:51 |只看该作者
我是老实人,我来也!
回复

使用道具 举报

5969

主题

1

听众

39万

积分

首席设计师

Rank: 8Rank: 8

纳金币
-1
精华
0

最佳新人 活跃会员 热心会员 灌水之王 突出贡献

7#
发表于 2013-2-11 23:18:11 |只看该作者
路过、路过、快到鸟,列位请继续...ing
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

手机版|纳金网 ( 闽ICP备2021016425号-2/3

GMT+8, 2025-7-19 16:52 , Processed in 0.200478 second(s), 29 queries .

Powered by Discuz!-创意设计 X2.5

© 2008-2019 Narkii Inc.

回顶部