The paper “Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network” and its source code is available here:
Addicted? Pick up cool perks on our Patreon page! –
A few comments with some of the best applications:
Lowell Camp – “This technology could be used for consumer-budget markerless facial motion capture, and if a follow-up paper enhances it with audio analysis for tongue posing, then it would require very little touch-up beyond a little temporal filtering.”
Milleoiseau – “VOIP in game but with face tracking.”
Evan – “Could this be used for some kind of automatic lip-reading system for deaf viewers to view live events?”
Matan – “Monitor emotions for product improvement.”
Idjles Erle – “Reconstructing ancestors faces from photos that are 150 years old. Working out from old photos who is more likely rested to whom.”
Morph Verse – “Maybe create a toolsets for artists to support easy correct anatomy tools in characters with facial and body features, for faster workflow in apps like Blender or 3ds.”
Bernard van Tonder – “Encourage others to watch educational content:
Let celebrities/sport idols teach important subjects by mapping their faces and voices onto people’s faces in educational videos.”
Adam de Anda – “Online shopping could get much more personalized. Send a selfie and be able to see sunglasses, hats, jewelry etc on your own face and able to rotate the image. Damn this actually pretty solid”
We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Andrew Melnychuk, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Esa Turkulainen, Geronimo Moralez, Lorin Atzberger, Malek Cellier, Marten Rauschenberg, Michael Albrecht, Michael Jensen, Nader Shakerin, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Torsten Reil.
One-time payment links are available below. Thank you very much for your generous support!
PayPal:
Bitcoin: 13hhmJnLEzwXgmgJN7RB6bWVdT7WkrFAHh
Ethereum: 0x002BB163DfE89B7aD0712846F1a1E53ba6136b5A
LTC: LM8AUh5bGcNgzq6HaV1jeaJrFvmKxxgiXg
Thumbnail background image credit:
Splash screen/thumbnail design: Felícia Fehér –
Károly Zsolnai-Fehér’s links:
Facebook:
Twitter:
Web:
source