TED2007
Blaise Agüera y Arcas: How PhotoSynth can connect the world's images
Blaise Agueray Arcas演示Photosynth
Filmed:
Readability: 4.3
5,831,957 views
Blaise Aguera y Arcas进行了炫目的Photosynth演示，这个软件可以改变我们观看数码图像的方式。使用从网上挑出的静态照片 ， Photosynth创建了叹为观止的梦幻景象，并且可以穿梭其中。
Blaise Agüera y Arcas - Software architect
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces. Full bio
Blaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces. Full bio
Double-click the English transcript below to play the video.
00:25
What I'm going to show you first, as quickly as I can,
0
0
2000
首先，我要用最快的速度为大家演示
00:27
is some foundational work, some new technology
1
2000
4000
一些新技术的基础研究成果。
00:31
that we brought to Microsoft as part of an acquisition
2
6000
3000
正好是一年前，微软收购了我们公司，
00:34
almost exactly a year ago. This is Seadragon,
3
9000
3000
而我们为微软带来了这项技术，它就是Seadragon。
00:37
and it's an environment in which you can either locally or remotely
4
12000
3000
Seadragon是一个软件环境，你可以通过它以近景或远景的方式
00:40
interact with vast amounts of visual data.
5
15000
3000
浏览浩瀚的可视化数据。
00:43
We're looking at many, many gigabytes of digital photos here
6
18000
3000
我们这里看到的是许多许多GB（千兆字节）级别的数码照片，
00:46
and kind of seamlessly and continuously zooming in,
7
21000
3000
对它们可以进行持续并且平滑的放大，
00:50
panning through the thing, rearranging it in any way we want.
8
25000
2000
可以通过全景的方式浏览它们，还可以对它们进行重新排列。
00:52
And it doesn't matter how much information we're looking at,
9
27000
4000
不管所见到的数据有多少、
00:56
how big these collections are or how big the images are.
10
31000
3000
图像集有多大以及图像本身有多大，Seadragon都拥有这样的处理能力。
00:59
Most of them are ordinary digital camera photos,
11
34000
2000
以上展示的图片大部分都是由数码相机拍摄的照片，
01:01
but this one, for example, is a scan from the Library of Congress,
12
36000
3000
但这个例子则不同，它是一张来自国会图书馆的扫描图片，
01:05
and it's in the 300 megapixel range.
13
40000
2000
拥有3亿个像素。
01:08
It doesn't make any difference
14
43000
1000
然而，浏览它并没有什么区别，
01:09
because the only thing that ought to limit the performance
15
44000
3000
因为限制系统性能的唯一因素只是：
01:12
of a system like this one is the number of pixels on your screen
16
47000
3000
你所使用的屏幕的像素数。
01:15
at any given moment. It's also very flexible architecture.
17
50000
3000
Seadragon同时也是一个非常灵活的架构。
01:18
This is an entire book, so this is an example of non-image data.
18
53000
3000
举个例子，这是一本完整的书，它的数据是非图像的(文本)。
01:22
This is "Bleak House" by Dickens. Every column is a chapter.
19
57000
5000
这是狄更斯所著的《荒凉山庄》，一列就是一章的内容。
01:27
To prove to you that it's really text, and not an image,
20
62000
4000
我给大家证明一下这真的是文本而非图片，
01:31
we can do something like so, to really show
21
66000
2000
我们可以这样操作，
01:33
that this is a real representation of the text; it's not a picture.
22
68000
3000
大家可以看出这真的是文本，而不是一幅图片。
01:37
Maybe this is a kind of an artificial way to read an e-book.
23
72000
2000
也许这会是一种阅读电子书的方式，
01:39
I wouldn't recommend it.
24
74000
1000
但是我可不推荐这么做。
01:40
This is a more realistic case. This is an issue of The Guardian.
25
75000
3000
接下来是一个更加实际的例子，这是一期《卫报》。
01:43
Every large image is the beginning of a section.
26
78000
2000
每一张大图片是一版开篇，
01:45
And this really gives you the joy and the good experience
27
80000
3000
而报纸或者杂志的纸质版本本身就包含了多种比例的图片，
01:48
of reading the real paper version of a magazine or a newspaper,
28
83000
5000
在阅读的时候，读者会得到更好的阅读体验，
01:54
which is an inherently multi-scale kind of medium.
29
89000
1000
从而享受阅读的乐趣。
01:56
We've also done a little something
30
91000
1000
我们在这里做了小小的改动
01:57
with the corner of this particular issue of The Guardian.
31
92000
3000
在这一期《卫报》得角上。
02:00
We've made up a fake ad that's very high resolution --
32
95000
3000
我们虚构了一个高分辨率的广告图片——
02:03
much higher than you'd be able to get in an ordinary ad --
33
98000
2000
这比你平常看到的普通广告的分辨率要高很多，
02:05
and we've embedded extra content.
34
100000
2000
在图片中嵌入了额外的内容。
02:07
If you want to see the features of this car, you can see it here.
35
102000
2000
如果你希望看到这辆车的特性，你可以看这里。
02:10
Or other models, or even technical specifications.
36
105000
4000
你还能看到其他的型号，甚至技术规格。
02:15
And this really gets at some of these ideas
37
110000
2000
这种方式在一定程度上
02:18
about really doing away with those limits on screen real estate.
38
113000
4000
避免了屏幕实际使用面积的限制。
02:22
We hope that this means no more pop-ups
39
117000
2000
我们希望这个技术能够减少不必要的弹出窗口
02:24
and other kind of rubbish like that -- shouldn't be necessary.
40
119000
2000
以及类似的垃圾信息。
02:27
Of course, mapping is one of those really obvious applications
41
122000
2000
显然，对于这项技术的应用，
02:29
for a technology like this.
42
124000
2000
数字地图也是显而易见的应用之一。
02:31
And this one I really won't spend any time on,
43
126000
2000
对此，我真的不想花费太多的时间进行介绍，
02:33
except to say that we have things to contribute to this field as well.
44
128000
2000
我只想告诉大家我们已经对这个领域做出了自己的贡献。
02:37
But those are all the roads in the U.S.
45
132000
2000
这些只是在NASA的地理空间图片基础上
02:39
superimposed on top of a NASA geospatial image.
46
134000
4000
进行叠加处理而得到的美国的道路地图。
02:44
So let's pull up, now, something else.
47
139000
2000
现在，我们先放下这些，看看其他的。
02:46
This is actually live on the Web now; you can go check it out.
48
141000
3000
实际上，这项技术已经放到网上了，大家可以自己去体验一下。
02:49
This is a project called Photosynth,
49
144000
1000
这个项目叫Photosynth，
02:51
which really marries two different technologies.
50
146000
1000
它实际上融合了两个不同的技术：
02:52
One of them is Seadragon
51
147000
1000
一个是Seadragon，
02:54
and the other is some very beautiful computer vision research
52
149000
2000
而另一个则是源自华盛顿大学的研究生Noah Snavely
02:57
done by Noah Snavely, a graduate student at the University of Washington,
53
152000
2000
所进行的计算机视觉研究的成果。
03:00
co-advised by Steve Seitz at U.W.
54
155000
2000
这项研究还得到了华盛顿大学Steve Seitz
03:02
and Rick Szeliski at Microsoft Research. A very nice collaboration.
55
157000
4000
和微软研究院Rick Szeliski的协助。这是一个非常漂亮的合作成果。
03:07
And so this is live on the Web. It's powered by Seadragon.
56
162000
2000
这个项目在互联网上已经得到应用了，它是基于Seadragon技术构建的。
03:09
You can see that when we kind of do these sorts of views,
57
164000
2000
你可以看到，我们轻松地对图片进行多种方式的查看，
03:12
where we can dive through images
58
167000
1000
从而能够对图片进行细致的剖析
03:14
and have this kind of multi-resolution experience.
59
169000
1000
并且拥有多分辨率的浏览体验。
03:16
But the spatial arrangement of the images here is actually meaningful.
60
171000
4000
不过，这些图片在三维空间的排列事实上是非常有意义的。
03:20
The computer vision algorithms have registered these images together
61
175000
3000
计算机视觉算法将这些图片联系到一起，
03:23
so that they correspond to the real space in which these shots --
62
178000
4000
那么这些图片就能够将真实空间呈现出来了，
03:27
all taken near Grassi Lakes in the Canadian Rockies --
63
182000
2000
而我们正是在这个空间里拍下了上述的照片——这些照片都是在
03:31
all these shots were taken. So you see elements here
64
186000
2000
加拿大落基山脉的格拉西湖（Grassi Lakes）附近拍下的——（所有照片）都是在这里拍下的。
03:33
of stabilized slide-show or panoramic imaging,
65
188000
4000
因此你可以看到这里的元素是稳定的幻灯放映或者全景成像，
03:40
and these things have all been related spatially.
66
195000
2000
而这些内容在空间上都是关联的。
03:42
I'm not sure if I have time to show you any other environments.
67
197000
3000
我不确定我们是否有时间来展示更多的环境全景。
03:45
There are some that are much more spatial.
68
200000
1000
有很多例子比这个的空间感还要强。
03:47
I would like to jump straight to one of Noah's original data-sets --
69
202000
3000
下面让我们来看一下去年夏天，
03:50
and this is from an early prototype of Photosynth
70
205000
2000
我们利用Noah早期的数据库之一
03:52
that we first got working in the summer --
71
207000
2000
所Photosynth的初期模型的建立。
03:54
to show you what I think
72
209000
1000
我认为
03:55
is really the punch line behind this technology,
73
210000
3000
这可谓是我们这项技术的最抢眼之处。
03:59
the Photosynth technology. And it's not necessarily so apparent
74
214000
2000
这项技术不单单像我们在
04:01
from looking at the environments that we've put up on the website.
75
216000
3000
网站上展示得那么简单明了。
04:04
We had to worry about the lawyers and so on.
76
219000
2000
主要因为我们制作网站时，要顾及到很多法律问题。
04:07
This is a reconstruction of Notre Dame Cathedral
77
222000
1000
这里是利用Flickr网站上
04:09
that was done entirely computationally
78
224000
2000
的图像重建的巴黎圣母院。
04:11
from images scraped from Flickr. You just type Notre Dame into Flickr,
79
226000
3000
你所要做的只是在Flickr网站上输入“巴黎圣母院”
04:14
and you get some pictures of guys in t-shirts, and of the campus
80
229000
3000
然后便能看到很多图片，包括留影的游人等等。
04:17
and so on. And each of these orange cones represents an image
81
232000
4000
所有这些橘黄颜色的锥形都代表了一张
04:22
that was discovered to belong to this model.
82
237000
2000
用来建立模型的图片。
04:26
And so these are all Flickr images,
83
241000
2000
这些全部是来自Flickr的图片，
04:28
and they've all been related spatially in this way.
84
243000
3000
被这样在空间里被串联起来。
04:31
And we can just navigate in this very simple way.
85
246000
2000
接着，我们便可如此自如的进行浏览。
04:35
(Applause)
86
250000
9000
（鼓掌）
04:44
You know, I never thought that I'd end up working at Microsoft.
87
259000
2000
说实话，我从来没想过我会最后来为微软工作
04:46
It's very gratifying to have this kind of reception here.
88
261000
4000
受到这样欢迎，真挺令人高兴的。
04:50
(Laughter)
89
265000
3000
（笑声）
04:53
I guess you can see
90
268000
3000
我想你们可以看出
04:56
this is lots of different types of cameras:
91
271000
2000
这些图片原自很多不同的相机：
04:58
it's everything from cell phone cameras to professional SLRs,
92
273000
3000
从手机摄像头到专业单反。
05:02
quite a large number of them, stitched
93
277000
1000
如此大量的不同质量的照片，全被在这个环境下
05:03
together in this environment.
94
278000
1000
拼合在了一起
05:04
And if I can, I'll find some of the sort of weird ones.
95
279000
2000
让我来找些比较诡异的图片。
05:08
So many of them are occluded by faces, and so on.
96
283000
3000
看，不少照片包含了游客的大头照等等。
05:13
Somewhere in here there are actually
97
288000
1000
我记得这儿应该有
05:15
a series of photographs -- here we go.
98
290000
1000
一个系列的照片 - 啊，在这儿。
05:17
This is actually a poster of Notre Dame that registered correctly.
99
292000
3000
这个是巴黎圣母院的海报。
05:21
We can dive in from the poster
100
296000
2000
我们可以钻到海报里
05:24
to a physical view of this environment.
101
299000
3000
去看整个重建的环境。
05:31
What the point here really is is that we can do things
102
306000
3000
这里的重点呢便是我们可以
05:34
with the social environment. This is now taking data from everybody --
103
309000
5000
有效地利用网络社区。我们可以从每个人那里得到数据
05:39
from the entire collective memory
104
314000
1000
将每个人对不同环境
05:40
of, visually, of what the Earth looks like --
105
315000
2000
的记忆收集在一起，
05:43
and link all of that together.
106
318000
1000
共建成模型。
05:44
All of those photos become linked together,
107
319000
2000
当所有这些图片交织在一起时，
05:46
and they make something emergent
108
321000
1000
所衍生出的
05:47
that's greater than the sum of the parts.
109
322000
2000
要远远超过单单收集起全部。
05:49
You have a model that emerges of the entire Earth.
110
324000
2000
这个模型所衍生出的，是整个地球。
05:51
Think of this as the long tail to Stephen Lawler's Virtual Earth work.
111
326000
5000
这如同是Stephen Lawler的《虚拟地球》的长尾市场。（Stephen Lawler 微软Virtual Earth项目主管）（见Long tail 长尾市场 TED: Chris Anderson ）
05:56
And this is something that grows in complexity
112
331000
2000
这类模型，会随着人们的
05:58
as people use it, and whose benefits become greater
113
333000
3000
使用而不断变的复杂，
06:01
to the users as they use it.
114
336000
2000
变得更加有价值。
06:03
Their own photos are getting tagged with meta-data
115
338000
2000
用户的照片，会被大家
06:05
that somebody else entered.
116
340000
1000
注上标签。
06:07
If somebody bothered to tag all of these saints
117
342000
3000
如果有人愿意为所有这些圣母院里的圣贤注上标签，
06:10
and say who they all are, then my photo of Notre Dame Cathedral
118
345000
3000
表明他们是谁，那我们的圣母院照片便会
06:13
suddenly gets enriched with all of that data,
119
348000
2000
一下子丰富起来，
06:15
and I can use it as an entry point to dive into that space,
120
350000
3000
然后呢，我们便能以这张照片为起点，进入这个空间，
06:18
into that meta-verse, using everybody else's photos,
121
353000
2000
这个由很多人的照片所搭建的虚拟世界，
06:21
and do a kind of a cross-modal
122
356000
2000
从而得到一种跨越模型，
06:25
and cross-user social experience that way.
123
360000
3000
跨越用户的交互体验。
06:28
And of course, a by-product of all of that
124
363000
1000
当然了，这一切所带来另外一个宝贵产物便是
06:30
is immensely rich virtual models
125
365000
2000
一个非常丰富的模型 - 充斥
06:32
of every interesting part of the Earth, collected
126
367000
2000
这地球每个角落里有趣的景观。这些景观不再
06:35
not just from overhead flights and from satellite images
127
370000
3000
局限于航空和卫星图片，
06:38
and so on, but from the collective memory.
128
373000
2000
而是实实在在的人们按下快门一刻所收藏的记忆的集合。
06:40
Thank you so much.
129
375000
2000
非常感谢！
06:42
(Applause)
130
377000
11000
（掌声）
06:53
Chris Anderson: Do I understand this right? That what your software is going to allow,
131
388000
4000
Chris Anderson: 如果我理解正确的话，你们的这个软件将能够
06:58
is that at some point, really within the next few years,
132
393000
2000
在未来的几年内
07:01
all the pictures that are shared by anyone across the world
133
396000
4000
将来自全球的图片
07:05
are going to basically link together?
134
400000
2000
接合在一起？
07:07
BAA: Yes. What this is really doing is discovering.
135
402000
2000
BAA:是的。这个软件的真正意义便是去探索。
07:09
It's creating hyperlinks, if you will, between images.
136
404000
3000
它在图片间构建起超链接。
07:12
And it's doing that
137
407000
1000
这个接合的过程
07:13
based on the content inside the images.
138
408000
1000
完全是基于图片的内容。
07:14
And that gets really exciting when you think about the richness
139
409000
3000
更令人兴奋的
07:17
of the semantic information that a lot of those images have.
140
412000
2000
在于图片所包含的大量文字语义信息。
07:19
Like when you do a web search for images,
141
414000
2000
比如，你在网上所以一张图片，
07:22
you type in phrases, and the text on the web page
142
417000
2000
键入关键词后，网页上的文字内容
07:24
is carrying a lot of information about what that picture is of.
143
419000
3000
将包含大量与这个图片相关的信息。
07:27
Now, what if that picture links to all of your pictures?
144
422000
2000
现在，假设这些图片全都与你的图片相连，那将会怎样？
07:29
Then the amount of semantic interconnection
145
424000
2000
那时，所以这些语义信息的相互链接
07:31
and the amount of richness that comes out of that
146
426000
1000
以及内容量将是
07:32
is really huge. It's a classic network effect.
147
427000
3000
巨大的。这将是非常典型的网络效应。
07:35
CA: Blaise, that is truly incredible. Congratulations.
148
430000
2000
CA:Blaise，太难以置信了。祝贺你们！
07:37
BAA: Thanks so much.
149
432000
1000
BAA:非常感谢各位！
ABOUT THE SPEAKER
Blaise Agüera y Arcas - Software architectBlaise Agüera y Arcas works on machine learning at Google. Previously a Distinguished Engineer at Microsoft, he has worked on augmented reality, mapping, wearable computing and natural user interfaces.
Why you should listen
Blaise Agüera y Arcas is principal scientist at Google, where he leads a team working on machine intelligence for mobile devices. His group works extensively with deep neural nets for machine perception and distributed learning, and it also investigates so-called "connectomics" research, assessing maps of connections within the brain.
Agüera y Arcas' background is as multidimensional as the visions he helps create. In the 1990s, he authored patents on both video compression and 3D visualization techniques, and in 2001, he made an influential computational discovery that cast doubt on Gutenberg's role as the father of movable type.
He also created Seadragon (acquired by Microsoft in 2006), the visualization technology that gives Photosynth its amazingly smooth digital rendering and zoom capabilities. Photosynth itself is a vastly powerful piece of software capable of taking a wide variety of images, analyzing them for similarities, and grafting them together into an interactive three-dimensional space. This seamless patchwork of images can be viewed via multiple angles and magnifications, allowing us to look around corners or “fly” in for a (much) closer look. Simply put, it could utterly transform the way we experience digital images.
He joined Microsoft when Seadragon was acquired by Live Labs in 2006. Shortly after the acquisition of Seadragon, Agüera y Arcas directed his team in a collaboration with Microsoft Research and the University of Washington, leading to the first public previews of Photosynth several months later. His TED Talk on Seadragon and Photosynth in 2007 is rated one of TED's "most jaw-dropping." He returned to TED in 2010 to demo Bing’s augmented reality maps.
Fun fact: According to the author, Agüera y Arcas is the inspiration for the character Elgin in the 2012 best-selling novel Where'd You Go, Bernadette?
Blaise Agüera y Arcas | Speaker | TED.com