After several days under the weather, I emerged today to several thousand unread feed items.
Normally to get through a lot of content, I scan the titles of the items for interesting stuff before reading further. Today, I think I passed up PhotoSketch (h/t Techmeme, Gizmodo) at least four times before it stuck, but when it did, wow. Just wow.
So, PhotoSketch is the work of several Chinese computer science students, and in a nutshell, it creates a montage of images based on freehand sketches.
In other words, you draw some stick-figure images, label them and PhotoSketch creates a composite image for you, like so:
That looks totally real to me. Unbelievable.
From the student’s abstract:
We present a system that composes a realistic picture from a simple freehand sketch annotated with text labels. The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet. Although online image search generates many inappropriate results, our system is able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images. We also provide a novel image blending algorithm to allow seamless image composition. Each blending result is given a numeric score, allowing us to find an optimal combination of discovered images. Experimental results show the method is very successful; we also evaluate our system using the results from two user studies.
Check out their video. This is incredible stuff, and if it’s ever made available to the interwebs, it will be a giant time-suck. Of course, licensing for the images used by PhotoSketch will be a rathole too, but hey, it’s still the coolest thing I’ve seen today.