東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Novel Workflow for Driving a 3D Face...

Sood, Prnav.

Linked to FindBook

Google Book

Amazon

博客來

Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes./
Author:	Sood, Prnav.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	39 p.
Notes:	Source: Masters Abstracts International, Volume: 83-01.
Contained By:	Masters Abstracts International83-01.
Subject:	Multimedia communications. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28546579
ISBN:	9798516930133

Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes.
Sood, Prnav.

Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 39 p.

Source: Masters Abstracts International, Volume: 83-01.

Thesis (M.S.)--Drexel University, 2021.

This item must not be sold to any third party vendors.

There have been many advances in technology over the years when it comes to animation. We have seen the industry transition from 2D animations from the 40s like Mickey Mouse to 3D animations like Toy Story. However, one of the issues that the industry still hasn't been able to resolve is recreating and animating a human face in a 3D environment without falling into the "uncanny valley". With this research, I propose a novel way to animate a 3D face using the deepfake technology. I started by initially training the deepfake model using real life footage of my face. I then created a realistic 3D face and used motion tracking technique to animate the 3D face using motion capture (mocap) in Blender. Moving forward, the pre-trained deepfake algorithm was used to drive the animation of the 3D head, and finally I compared the mocap and the deepfake animations by conducting a survey. There were a few areas where one of the animations was perceived favourably over the other, however the overall perception of the animations was similar on the majority of the factors, which can be attributed to a few limitations mentioned in the paper.

ISBN: 9798516930133Subjects--Topical Terms:

590562
Multimedia communications.
Subjects--Index Terms:

3D face rig

Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes.
LDR:02287nmm a2200373 4500 001 2282100
005 20210927083540.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798516930133
035 $a (MiAaPQ)AAI28546579
035 $a AAI28546579
040 $a MiAaPQ $c MiAaPQ
100 1 $a Sood, Prnav. $3 3560848
245 1 0 $a Novel Workflow for Driving a 3D Face Rig from a Reference Video using Deepfakes.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 39 p.
500 $a Source: Masters Abstracts International, Volume: 83-01.
500 $a Includes supplementary digital materials.
500 $a Advisor: Mauriello, David A.
502 $a Thesis (M.S.)--Drexel University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a There have been many advances in technology over the years when it comes to animation. We have seen the industry transition from 2D animations from the 40s like Mickey Mouse to 3D animations like Toy Story. However, one of the issues that the industry still hasn't been able to resolve is recreating and animating a human face in a 3D environment without falling into the "uncanny valley". With this research, I propose a novel way to animate a 3D face using the deepfake technology. I started by initially training the deepfake model using real life footage of my face. I then created a realistic 3D face and used motion tracking technique to animate the 3D face using motion capture (mocap) in Blender. Moving forward, the pre-trained deepfake algorithm was used to drive the animation of the 3D head, and finally I compared the mocap and the deepfake animations by conducting a survey. There were a few areas where one of the animations was perceived favourably over the other, however the overall perception of the animations was similar on the majority of the factors, which can be attributed to a few limitations mentioned in the paper.
590 $a School code: 0065.
650 4 $a Multimedia communications. $3 590562
650 4 $a Computer science. $3 523869
653 $a 3D face rig
653 $a Animation
653 $a Deepfake
653 $a Motion capture
653 $a Workflow
690 $a 0558
690 $a 0984
710 2 $a Drexel University. $b Digital Media (Westphal College of Media Arts and Design). $3 3342374
773 0 $t Masters Abstracts International $g 83-01.
790 $a 0065
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28546579