So, who is the first to dig out some pictures that were 'redacted before publication' and can be de-obfuscated this way?
So, who is the first to dig out some pictures that were 'redacted before publication' and can be de-obfuscated this way?
Here's one famous example https://en.wikipedia.org/wiki/Christopher_Paul_Neil
There's a bunch of other image processing stuff that can be done. Identifying location from sparse clues is important. Identifying wall paper patterns, or coca-cola bottle labels gives clues.
Indeed, there is no free lunch. This is only possible because the restoration algorithms are making some rather strong assumptions about the original picture. For example, they assume that evey blury area in the blury picture has a corresponding sharp edge in the original picture.
It works fairly well on pictures with a lot of sharp edges such as the ones in the article: buldings, text etc.
I'm guessing that it wouldn't work as well on natural landscapes or human faces, because they don't usually have edges likes this.
For example, in this restored picture,
http://hsto.org/storage2/9d8/554/c15/9d8554c156e63a213797502...
the sky in this picture contains edges that do no exist in the original picture. The algorithm is trying to find edges where there are none. This is a very visible impact of this assumption.