Just-in-time, viable, 3D avatars from scans

Andrew Feng, Evan Suma, Ari Shapiro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We demonstrate a system that can generate a photorealistic, interactive 3D character from a human subject that is capable of movement, emotion, speech and gesture in less than 20 minutes without the need for 3D artist intervention or specialized technical knowledge through a near automatic process. Our method uses mostly commodity- or of-the-shelf hardware. We demonstrate the just-in-time use of generating such 3D models for virtual and augmented reality, games, simulation and communication. We anticipate that the inexpensive generation of such photorealistic models will be useful in many venues where a just-in-time 3D construction of digital avatars that resemble particular human subjects is necessary. Figure 1 shows the overall workflow of our virtual character creation pipeline.

Original languageEnglish (US)
Title of host publicationACM SIGGRAPH 2017 Talks, SIGGRAPH 2017
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450350082
DOIs
StatePublished - Jul 30 2017
Externally publishedYes
EventACM SIGGRAPH 2017 Talks - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2017 - Los Angeles, United States
Duration: Jul 30 2017Aug 3 2017

Publication series

NameACM SIGGRAPH 2017 Talks, SIGGRAPH 2017

Other

OtherACM SIGGRAPH 2017 Talks - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2017
Country/TerritoryUnited States
CityLos Angeles
Period7/30/178/3/17

Bibliographical note

Publisher Copyright:
© Copyright 2017 Authors.

Keywords

  • 3d
  • Animation
  • Avatar
  • Photogrammetry
  • RGB-D
  • Rigging
  • Scanning
  • Skinning
  • Virtual reality

Fingerprint

Dive into the research topics of 'Just-in-time, viable, 3D avatars from scans'. Together they form a unique fingerprint.

Cite this