Harvard Group Takes Complexity Out of Video Face Replacement

December 6th, 2011

Via: PhysOrg:

The tool claims to be able to replace faces using only single-camera video with minimal user input. The software can render a ten-second video in about twenty minutes. The software is promoted as a system that can be used by amateur and budget-wary film makers.

Kevin Dale, part of the school’s Graphics, Vision and Interaction (GVI) Group, is co-author of a paper, “Video Face Replacement,” which discusses the approach. The facial replacement method used, according to the authors, requires no substantial manual operations or complex hardware, only single-camera video.

Research Credit: noncompliant

4 Responses to “Harvard Group Takes Complexity Out of Video Face Replacement”

  1. brandon says:

    Wow, so it should be pretty easy to show innocent people committing crimes.. Bummer

  2. pessimistic optimist says:

    the final composite looks strangely familiar somehow, tho i cant place where ive seen something like it. just slightly off, like uncanny valley almost, but different.

  3. Kevin says:

    The ‘young’ Jeff Bridges scenes in TRON: Legacy?

  4. pookie says:

    @brandon Yeah, and it’s already easy to show innocent people committing crimes via “recorded” phone conversations as evidence — conversations that have been digitally assembled from several different sources.

    http://freedominourtime.blogspot.com/2011/10/framing-steele-case-study-of-sovietized.html

Leave a Reply

You must be logged in to post a comment.