Visual Smash Up by Parag K Mital
One of many projects by the author experimenting with real-time video processing of ‘mosaicing visual content’. The end results are somewhere around hallucinary Cubism, datamoshing and moving collage - video below:
We present a system for realtime mosaicing of visual content. The system learns objects from the camera image and displays the resulting visual mosaic. Only unique objects are learned creating a hallucinatory resynthesis of the original camera image. For instance, all keyboard letters are replaced by only a single letter since based on purely visual appearance, a single letter is unique enough to portray the keyboard.
It is worth checking out other projects by Parag, including an iOS app which can do something similar with your photo images. Oddly, it requires you to allow location data to be available which seems irrelevant, so I didn’t test it. The app, though, is free.