-
It’s the most wonderful time of the year (SIGGRAPH, that is)
All kinds of interesting new research and projects will be popping up over the next couple days!
Check out this one:
3D Object Manipulation in a Single Photograph using Stock 3D Models
Natasha Kholgade 1, Tomas Simon 1, Alexei Efros 2, Yaser Sheikh 11 Carnegie Mellon University
2 University of California, Berkeleyhttps://www.youtube.com/watch?v=bMeBvrG9Uyo
Walter Soyka
Designer & Mad Scientist at Keen Live [link]
Motion Graphics, Widescreen Events, Presentation Design, and Consulting
@keenlive | RenderBreak [blog] | Profile [LinkedIn]Some contents or functionalities here are not available due to your cookie preferences!This happens because the functionality/content marked as “Google Youtube” uses cookies that you choosed to keep disabled. In order to view this content or use this functionality, please enable cookies: click here to open your cookie preferences.
-
6 Replies
-
Egads! Remarkable.
-
Wow!
-
Awesome! Really want a taxi that can do flips, fly and all that super cool stuff. Something of a FCP X type of roller coaster, no tracks!
I am an avid user of FCP X!
-
I just want to throw my chair down the hall when things get silly.
-
I feel really stoopid right now…
It was at a Vegas premiere that I resolved to become an avid FCPX user.
Lance Bachelder
Writer, Editor, Director
Downtown Long Beach, California
https://www.imdb.com/name/nm1680680/?ref_=fn_al_nm_1 -
Automatic Editing of Footagefrom Multiple Social Cameras
*Ido Arev 1,3, *Hyun Soo Park 2, Yaser Sheikh 2,3, Jessica Hodgins 2,3, and Ariel Shamir 1,3
1 The Interdisciplinary Center Herzliya
2 Carnegie Mellon University
3 Disney Research Pittsburgh
* Both authors contributed equally to this work.https://graphics.cs.cmu.edu/projects/social-cameras/
This one is about automating editing, in a very specific domain.
The software analyzes footage from multiple “social cameras” — wearable cameras, cell phone cameras, etc. It solves the 3D scene, including the position of all cameras, then assumes that the thing most cameras are looking at is the correct subject (joint attention estimation), then performs a multi-cam edit.
It cuts between cameras as necessary to try to keep the best shot, cutting on action when possible, and avoiding jump cuts or 180-degree rule violations.
Walter Soyka
Designer & Mad Scientist at Keen Live [link]
Motion Graphics, Widescreen Events, Presentation Design, and Consulting
@keenlive | RenderBreak [blog] | Profile [LinkedIn]
Reply to this Discussion! Login or Sign Up