Blaise Aguera y Arcas: Jaw-dropping Photosynth demo

What I'm going to show you first, as quickly as I can,

Nitakachowaonyesha kwanza, haraka niwezavyo,

is some foundational work, some new technology

ni kazi ya msingi, katika teknolojia mpya

that we brought to Microsoft as part of an acquisition

ambayo tuliingiza Microsoft kama sehemu ya ununuzi wa kampuni

almost exactly a year ago.

takriban mwaka mmoja uliopita. Hii ni Seadragon.

This is Seadragon, and it's an environment

Na ni mfumo ambao unaweza, kwa karibu au mbali,

in which you can either locally or remotely interact

with vast amounts of visual data.

kujiunganisha na kufanyia kazi takwimu mbalimbali za picha.

We're looking at many, many gigabytes of digital photos here

Hapa tunaziangalia nyingi, katika kipimo cha picha cha gigabyte

and kind of seamlessly and continuously zooming in,

na bila kukatika na kwa kuendelea kukuza mfululizo,

panning through it, rearranging it in any way we want.

kulengesha kwenye kitu, kuirekebisha vile tutakavyo.

And it doesn't matter how much information we're looking at,

Bila kujali taarifa ngapi tunaziangalia,

how big these collections are or how big the images are.

zina ukubwa gani au nyingi kiasi gani.

Most of them are ordinary digital camera photos,

Nyingi kati yake ni picha za kawaida zilizopigwa na kamera za dijito,

but this one, for example, is a scan from the Library of Congress,

hii hapa, kwa mfano, ni kivuli cha picha kutoka Maktaba ya Bunge,

and it's in the 300 megapixel range.

na iko katika kipimo cha vipandepicha 300.

It doesn't make any difference

Haileti tofauti yeyote

because the only thing that ought to limit the performance of a system like this one

kwasababu kitu pekee kitakachoweza kuzuia ufanisi

wa mfumo kama huu ni idadi ya vipandepicha kwenye skrini yako

is the number of pixels on your screen at any given moment.

It's also very flexible architecture.

wakati wowote. Huu ni usanifu huria.

This is an entire book, so this is an example of non-image data.

Hiki ni kitabu kizima, mfano wa takwimu ambazo si picha.

This is "Bleak House" by Dickens.

Hiki ni Bleak House kilichoandikwa na Dickens. Kila safu ni sura.

Every column is a chapter.

To prove to you that it's really text, and not an image,

Kuwathibitishia kwamba haya ni maandishi, na siyo picha,

we can do something like so, to really show

tunaweza kufanya kama hivi, ili kuweza kuonyesha

that this is a real representation of the text; it's not a picture.

kuwa hiki ni kielelezo cha maandishi: na siyo picha.

Maybe this is an artificial way to read an e-book.

Labda hii ni njia nyingine ya kusoma kitabu cha nakala za elektroniki.

I wouldn't recommend it.

Siwezi kuipendekeza.

This is a more realistic case, an issue of The Guardian.

Huu ni mfano wa ukweli. Hili ni toleo la The Guardian.

Every large image is the beginning of a section.

Kila picha kubwa ni mwanzo wa sura.

And this really gives you the joy and the good experience

Hii inakupa raha na uzoefu mzuri

of reading the real paper version of a magazine or a newspaper,

wa kusoma tolea halisi la jarida au gazeti,

which is an inherently multi-scale kind of medium.

ambalo mara nyingi chombo cha habari chenye kina na mapana.

We've done something

Pia tumefanya kitu kidogo

with the corner of this particular issue of The Guardian.

kwenye kona ya toleo hili la The Guardian.

We've made up a fake ad that's very high resolution --

Tumetengeneza tangazo la uongo na ambalo liko katika kiwango cha juu sana --

much higher than in an ordinary ad --

kuliko ambavyo ungeweza kuona kwenye tangazo la kawaida --

and we've embedded extra content.

na tumeongezea vitu vya ziada.

If you want to see the features of this car, you can see it here.

Kama unataka kujua taarifa za undani wa gari hili, unaweza kuziona hapa.

Or other models, or even technical specifications.

Au miundo mingine, au hata maelezo ya kina ya kiufundi.

And this really gets at some of these ideas

Hii inaingia katika baadhi ya haya mawazo

about really doing away with those limits on screen real estate.

katika kuondokana na vikwazo vya ufanisi wa skrini

We hope that this means no more pop-ups

Tunatumaini kwamba hii ina maana kwamba hakutakuwa na vipeperushitovuti tena

and other rubbish like that -- shouldn't be necessary.

na taka nyingine kama hizo -- hazitakuwa muhimu.

Of course, mapping is one of those obvious applications

hakika, ramani zitakuwa moja ya matumizi muhimu ya

for a technology like this.

teknolojia kama hii

And this one I really won't spend any time on,

Na sitapoteza muda kwenye hili,

except to say that we have things to contribute to this field as well.

isipokuwa kwamba tuna vitu vya kuchangia katika eneo hili pia.

But those are all the roads in the U.S.

Lakini hizi zote ni barabara za Marekani

superimposed on top of a NASA geospatial image.

zilizowekwa juu ya picha za kijiografia za NASA

So let's pull up, now, something else.

Sasa hebu tuangalie kitu kingine.

This is actually live on the Web now; you can go check it out.

Hii ipo hewani kwenye mtando kwa sasa; unaweza kwenda na kuiangalia.

This is a project called Photosynth, which marries two different technologies.

Huu ni mradi unaoitwa Photosynth,

ambao unajumuisha teknolojia mbili tofauti.

One of them is Seadragon

Mojawapo ni Seadragon

and the other is some very beautiful computer-vision research

na nyingine ni ya utafiti wa kuona katika kompyuta

done by Noah Snavely, a graduate student at the University of Washington,

uliofanywa na Noah Snavely, mwanafunzi wa chuo kikuu cha Washington,

co-advised by Steve Seitz at U.W.

na kushauriwa na Steve Seitz hapo UW

and Rick Szeliski at Microsoft Research.

na Rick Szeliski katika kitengo cha utafiti cha Microsoft. Ushirikiano mzuri sana.

A very nice collaboration.

And so this is live on the Web. It's powered by Seadragon.

Kwa hiyo hii iko hewani kwenye mtandao. Na imewezeshwa na Seadragon.

You can see that when we do these sorts of views,

Unaweza kuona wakati tukifanya vielelezo hivi,

where we can dive through images

ambapo tunaweza kuzamia kwenye picha

and have this kind of multi-resolution experience.

na kuwa na aina hii ya kuweza kuona taswira mbalimbali.

But the spatial arrangement of the images here is actually meaningful.

Lakini hapa mpangalio wa mahusiano ya picha unaleta maana zaidi.

The computer vision algorithms have registered these images together

Miundonamba ya picha za kompyuta imezisajiri hizi picha pamoja,

so that they correspond to the real space in which these shots --

ili ziendane na sehemu halisi ambako picha hizi zilipigwa --

all taken near Grassi Lakes in the Canadian Rockies --

zote zilipigwa karibu na Ziwa Grassi huko Canadian Rockies --

all these shots were taken.

zilichukuliwa. Kwa hiyo unaona vipengee hapa

So you see elements here

of stabilized slide-show or panoramic imaging,

za vielelezopicha vilivyokamilika au picha za kupita.

and these things have all been related spatially.

na vitu hivi vyote vimehusianishwa pamoja.

I'm not sure if I have time to show you any other environments.

Sina uhakika kama nina muda wa kuwaonyesha taswira nyingine.

Some are much more spatial.

Kunamengine ambayo yanahusiana zaidi.

I would like to jump straight to one of Noah's original data-sets --

Nitaenda moja kwa moja kwenye moja ya seti za takwimu halisi za Noah --

this is from an early prototype that we first got working this summer --

na hii inatoka kwenye toleo la mfano la Photosynth ya awali

ambayo tuliipata wakati tukifanya kazi majira ya joto --

to show you what I think

kukuonyesha ninachokifikiria

is really the punch line behind the Photosynth technology,

ni mzaha tu wa teknolojia hii,

It's not necessarily so apparent

teknolojia ya Photosynth. Na si dhahiri sana

from looking at the environments we've put up on the website.

kwa kuangalia katika mfumo tuliouweka kwenye tovuti.

We had to worry about the lawyers and so on.

Ilibidi tuanze kuhofia juu ya wanasheria na mengineyo.

This is a reconstruction of Notre Dame Cathedral

Huu ni ujengwaji tena wa kanisa kuu la dayosisi ya Notre Dame

that was done entirely computationally from images scraped from Flickr.

ambao ulifanywa kwa kwakutumia kompyuta peke yake

kutoka kwenye picha zilizopatikana kwenye Flickr. Unaandika Notre Dame kwenye Flickr,

You just type Notre Dame into Flickr,

and you get some pictures of guys in T-shirts, and of the campus and so on.

na unapata picha za watu waliovaa T-shirts, na za eneo la chuo

na mengineyo. Na kati ya kila hizi pia za rangi ya chungwa zinawakilisha taswira

And each of these orange cones represents an image

that was discovered to belong to this model.

ambazo ziligunduliwa zinauhusiano na muundo huu.

And so these are all Flickr images,

Na hizi zote ni picha za Flickr,

and they've all been related spatially in this way.

na zote zimehusishwa kwa njia hii.

We can just navigate in this very simple way.

Na tunaweza kutembelea kwa njia hii rahisi.

(Applause)

(Makofi).

(Applause ends)

You know, I never thought that I'd end up working at Microsoft.

Unajua, sikufikiria kuwa nitakuja kufanya kazi Microsoft.

It's very gratifying to have this kind of reception here.

Ni faraja kubwa sana kupata mapokezi kama haya hapa.

(Laughter)

(Kicheko).

I guess you can see this is lots of different types of cameras:

Natumaini mnaweza kuona

hizi ni kamera nyingi tofauti:

it's everything from cell-phone cameras to professional SLRs,

ni kila kitu kutoka kwenye kamera za simu za mkononi mpaka kamera za kitaalam za SLRs,

quite a large number of them, stitched together in this environment.

ni nyingi, zikiwa pamoja

katika mfumo huu.

If I can find some of the sort of weird ones --

Na kama nitaweza, nitatafuta zile za ajabu.

So many of them are occluded by faces, and so on.

Nyingi zao zimezibwa kwa sura za watu, na mengineyo

Somewhere in here there is actually a series of photographs -- here we go.

Kati ya hapo kuna

mlolongo wa picha -- naam hapa.

This is actually a poster of Notre Dame that registered correctly.

Hii hakika ni picha ya Notre Dame ambayo imesajiliwa kwa usahihi.

We can dive in from the poster

Tunaweza kuingia ndani ya picha

to a physical view of this environment.

katika mazingira ya maumbile yake.

What the point here really is

Cha muhimu hapa ni nini tunaweza kufanya

is that we can do things with the social environment.

na mfumo huu. Hii ni kuchukua takwimu kutoka kwa kila mtu --

This is now taking data from everybody --

from the entire collective memory, visually, of what the Earth looks like --

kutoka katika mkusanyiko wa kumbukumbu

za taswira, namna dunia ilivyo --

and link all of that together.

na kuzijumuisha zote.

Those photos become linked, and they make something emergent

Picha zote zinaunganishwa pamoja,

na zinafanya kitu kutokea

that's greater than the sum of the parts.

ambacho ni kubwa zaidi ya jumla ya sehemu ndogondogo.

You have a model that emerges of the entire Earth.

Una mfano ambao unatokea katika dunia nzima.

Think of this as the long tail to Stephen Lawler's Virtual Earth work.

Fikiria hii ni kama mkia mrefu wa kazi za picha za dunia za Stephen Lawler.

And this is something that grows in complexity as people use it,

Na hiki kitu ambacho kinakua na kuongeza mchangamano

jinsi watu wanavyotumia, na faida yake inakuwa kubwa

and whose benefits become greater to the users as they use it.

kwa watumiaji jinsi wanavyotumia.

Their own photos are getting tagged with meta-data that somebody else entered.

Picha zao zinaunganishwa na meta-data

ambavyo mtu mwingine ameviingiza.

If somebody bothered to tag all of these saints

Kama kuna mtu angewaunganisha watakatifu hawa wote

and say who they all are, then my photo of Notre Dame Cathedral

na kusema wao ni akina nani, kwa hiyo picha yangu ya kanisa kuu la Notre Dame

suddenly gets enriched with all of that data,

ingeboreshwa na vielelezo hivyo vyote,

and I can use it as an entry point to dive into that space,

na ninaweza kuitumia kama njia ya kuingia katika sehemu hiyo,

into that meta-verse, using everybody else's photos,

katika takwimumaneno, kwa kutumia picha za watu wengine,

and do a kind of a cross-modal

na kufanya mwingiliano

and cross-user social experience that way.

na mwingiliano wa watumiaji kwa njia hiyo.

And of course, a by-product of all of that is immensely rich virtual models

Na kwa hakika, matokeo ya yote hayo

ni mifumo thabiti ya picha

of every interesting part of the Earth,

wa kila sehemu ya dunia, iliyokusanywa

collected not just from overhead flights and from satellite images

siyo tu kwa angani na kutoka kwenye picha za setilaiti

and so on, but from the collective memory.

na mengineyo, bali kutoka kwenye majumuisho ya kumbukumbu.

Thank you so much.

Asanteni sana.

(Applause)

(Makofi).

(Applause ends)

Chris Anderson: Do I understand this right?

Chris Anderson: Nimekuelewa? Kuwa programu yako itaruhusu,

What your software is going to allow,

is that at some point, really within the next few years,

kuwa, wakati fulani, katika kipindi cha miaka michache ijayo,

all the pictures that are shared by anyone across the world

picha zote zitakazokuwa zikigawanwa na mtu yeyote duniani

are going to link together?

zitaunganishwa pamoja?

BAA: Yes. What this is really doing is discovering,

BAA: Ndiyo. Kinachotokea hapa ni uvumbuzi.

creating hyperlinks, if you will, between images.

Inatengeneza viuongotovuti, kati ya picha.

It's doing that based on the content inside the images.

Na inafanya hivyo

ikitegemea yaliyomo ndani ya picha.

And that gets really exciting when you think about the richness

Hii inaleta msisimko zaidi ukifikiria kuhusu ubora

of the semantic information a lot of images have.

wa taarifa zilizomo kwenye picha hizo.

Like when you do a web search for images,

Kwa mfano ukiwa unatafuta picha kwenye mtandao,

you type in phrases,

unaandika vifungu vya maneno na maandishi katika ukurasa wa tovuti

and the text on the web page is carrying a lot of information

inabeba taarifa kuhusu picha hiyo ni ya nini.

about what that picture is of.

What if that picture links to all of your pictures?

Sasa, itakuwaje kama picha hiyo inaunganisha picha zako zote?

Hapo idadi ya miunganiko ya taarifa

The amount of semantic interconnection and richness

na idadi ya ubora ambao unakuja pamoja nayo

that comes out of that is really huge.

ni kubwa sana. Ni matokeo ya kiwango cha juu cha muungano wa mtandao.

It's a classic network effect.

CA: Truly incredible. Congratulations.

CA: Blaise, hii ni nzuri sana. Hongera.

BAA: Asante sana