{"id":548,"date":"2006-11-10T15:19:43","date_gmt":"2006-11-10T20:19:43","guid":{"rendered":"http:\/\/blogs.law.harvard.edu\/hoanga\/2006\/11\/10\/photosynth-a-new-way-of-seeing-relatio"},"modified":"2006-11-10T15:19:43","modified_gmt":"2006-11-10T20:19:43","slug":"photosynth-a-new-way-of-seeing-relations-in-your-photo-collection","status":"publish","type":"post","link":"https:\/\/archive.blogs.harvard.edu\/hoanga\/2006\/11\/10\/photosynth-a-new-way-of-seeing-relations-in-your-photo-collection\/","title":{"rendered":"Photosynth, a new way of seeing relations in your photo collection"},"content":{"rendered":"

<\/a><\/p>\n

<\/p>\n

<\/p>\n

<\/a><\/p>\n

I just took a glance at <\/p>\n

photosynch<\/a> and<\/p>\n

am really impressed with the applications of computer vision and image<\/p>\n

processing techniques to create a really unique application.<\/p>\n

The basic<\/p>\n

idea is to take a pile of photos that are related to each other somehow<\/p>\n

(imagine taking zillions of pictures of the Taj Mahal from tons of<\/p>\n

different places) find similar features in all the images and try to<\/p>\n

reconstruct a mock 3d space that shows the spacial relation between<\/p>\n

all of your photos. This is really cool as you might be able to create<\/p>\n

a very interesting photo tour from your photo collection in a 3d<\/p>\n

navigatable space.<\/p>\n

Oddly, I was trying to come up with a similar idea to link videos stills<\/p>\n

in QuickTimeVR movies and try to use the linkable features in QuicktimeVR<\/p>\n

to provide clickable hotspots that would take you to another photo that<\/p>\n

was a picture of the same scene however this is far slicker and if it works<\/p>\n

with very little intervention from the user besides pointing to a pile<\/p>\n

of photos and letting it do its job that would be great.<\/p>\n

However, there are still caveats. The whole process takes hours or days<\/p>\n

to currently do and the current technology preview is only for a pre-rendered<\/p>\n

project. The true acid test will be in my opinion the ability to<\/p>\n

just point to a folder of pictures and have it do its job with as little<\/p>\n

possible human intervention as possible. That is a not a trivial problem<\/p>\n

but I’m sure we’ll see something interesting especially since it has<\/p>\n

two<\/a> (very well)<\/p>\n

known<\/a> researchers<\/p>\n

in the computer vision field. I’m really looking forward to the results<\/p>\n

of their labor. My last question is how many technologies behind this<\/p>\n

are patented already. It’d be great if it an OSS implementation inspired<\/p>\n

from this project could be made however patents are a sticky problem.<\/p>\n

Try it yourself<\/a><\/p>\n

( 6 or 7 REQUIRED)<\/p>\n","protected":false},"excerpt":{"rendered":"

I just took a glance at photosynch and am really impressed with the applications of computer vision and image processing techniques to create a really unique application. The basic idea is to take a pile of photos that are related to each other somehow (imagine taking zillions of pictures of the Taj Mahal from tons […]<\/p>\n","protected":false},"author":704,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1212],"tags":[],"class_list":["post-548","post","type-post","status-publish","format-standard","hentry","category-tagme"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/posts\/548","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/users\/704"}],"replies":[{"embeddable":true,"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/comments?post=548"}],"version-history":[{"count":0,"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/posts\/548\/revisions"}],"wp:attachment":[{"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/media?parent=548"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/categories?post=548"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/archive.blogs.harvard.edu\/hoanga\/wp-json\/wp\/v2\/tags?post=548"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}