Building time lapse videos from community photographs is an incredibly difficult and laborious task: these photos were taken at a different part of the year, from different times of the day, with different viewpoints and cameras. A good algorithm should try to equalize these images and bring them to a common denominator to get rid of the commonly seen flickering effect. Researchers at the University of Washington and Google nailed this regularization in their newest work that they showcased at SIGGRAPH 2015. Check out the video for the details!
Photograph credits in the video:
Flickr user dration, Zack Lee, Nadav Tobias, Juan Jesus Orío and Klaus Wißkirchen.
In the original paper, photographs from the following Flickr users were reproduced under Creative Commons license: Aliento Más Allá, jirihnidek, mcxurxo, elka cz, Daikrieg, Free the image, Cebete and ToastyKen.
The paper “Time-lapse Mining from Internet Photos” is available here:
Disclaimer: I was not part of this research project, I am merely providing commentary on this work.
Thumbnail background by Davidw:
Subscribe if you would like to see more of these! –
Károly Zsolnai-Fehér’s links:
Patreon →
Facebook →
Web →
Twitter →
source