Getting the Face Behind the Squares: Reconstructing Pixelized Video Streams

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Defeating Image Obfuscation with Deep Learning (2016, background): “Cavedon et al. [6] exploited the changes in pixel boxes for obfuscating video frames to reconstruct pixelated videos using image processing methods so that humans can identify objects in the re-constructed images.”
On the (In)effectiveness of Mosaicing and Blurring as Tools for Document Redaction (2016, background): “Likewise, Cavedon, Foschini, and Vigna[1] used superresolution techniques to recover mosaiced faces from video, assuming that the subjects on video did not move much between consecutive frames.”