Uploaded December 2018 | Updated September 2026, 23 hours ago
The Reality Lab Lectures - Tuesday, October 30th, 2018
Talk Title: Creating Photoreal Digital Actors (and Environments) for Movies, Games, and Virtual Reality
Speaker: Paul Debevec (Senior Scientist, Google VR)
Talk Abstract: Presenting recent work from USC ICT and Google VR for recording and rendering photorealistic actors and environments for movies, games, and virtual reality. The Light Stage facial scanning systems are geodesic spheres of inward-pointing LED lights which have been used to help create digital actors based on real people in movies such as Avatar, Benjamin Button, Maleficent, Furious 7, Blade Runner: 2049, and Ready Player One. Light Stages can also reproduce recorded omnidirectional lighting environments and have recently been extended with multispectral LED lights to accurately mimic the color rendition properties of daylight, incandescent, and mixed lighting environments. Our full-body Light Stage 6 system was used in conjunction with natural language processing and an automultiscopic projector array to record and project interactive hologram-like conversations with survivors of the Holocaust. I will conclude the talk by presenting Google VR's "Welcome to Light Fields", the first downloadable virtual reality light field experience which records and displays 360 degree photographic environments that you can move around inside of with six degrees of freedom, creating VR experiences which are far more comfortable and immersive.
Event held on the UW-Seattle Campus and recorded by UW CSE Production Team
© UW Reality Lab, 2018
http://realitylab.uw.edu
The Reality Lab Lectures - Tuesday, October 30th, 2018
Talk Title: Creating Photoreal Digital Actors (and Environments) for Movies, Games, and Virtual Reality
Speaker: Paul Debevec (Senior Scientist, Google VR)
Talk Abstract: Presenting recent work from USC ICT and Google VR for recording and rendering photorealistic actors and environments for movies, games, and virtual reality. The Light Stage facial scanning systems are geodesic spheres of inward-pointing LED lights which have been used to help create digital actors based on real people in movies such as Avatar, Benjamin Button, Maleficent, Furious 7, Blade Runner: 2049, and Ready Player One. Light Stages can also reproduce recorded omnidirectional lighting environments and have recently been extended with multispectral LED lights to accurately mimic the color rendition properties of daylight, incandescent, and mixed lighting environments. Our full-body Light Stage 6 system was used in conjunction with natural language processing and an automultiscopic projector array to record and project interactive hologram-like conversations with survivors of the Holocaust. I will conclude the talk by presenting Google VR's "Welcome to Light Fields", the first downloadable virtual reality light field experience which records and displays 360 degree photographic environments that you can move around inside of with six degrees of freedom, creating VR experiences which are far more comfortable and immersive.
Event held on the UW-Seattle Campus and recorded by UW CSE Production Team
© UW Reality Lab, 2018
http://realitylab.uw.edu


![Teaser Video: Lifespan Age Transformation Synthesis
VIDEO: 60-second Teaser video [FULL project video: https://youtu.be/9fulnt2_q_Y]
TITLE: Lifespan Age Transformation Synthesis
AUTHORS: Roy Or-El, Soumyadip Sengupta, Ohad Fried, Eli Shechtman, Ira Kemelmacher-Shlizerman
ABSTRACT: We address the problem of single photo age progression and regression the prediction of how a person might look in the future, or how they looked in the past. Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process. This limits the applicability of previous methods to aging of adults to slightly older adults, and application of those methods to photos of children does not produce quality results. We propose a novel multi-domain image-to-image generative adversarial network architecture, whose learned latent space models a continuous bi-directional aging process. The network is trained on the FFHQ dataset, which we labeled for ages, gender, and semantic segmentation. Fixed age classes are used as anchors to approximate continuous age transformation. Our framework can predict a full head portrait for ages 0 70 from a single photo, modifying both texture and shape of the head. We demonstrate results on a wide variety of photos and datasets, and show significant improvement over the state of the art.
CODE: https://github.com/royorel/Lifespan_Age_Transformation_Synthesis
COLAB DEMO: https://colab.research.google.com/github/royorel/Lifespan_Age_Transformation_Synthesis/blob/master/LATS_demo.ipynb
DATA: https://github.com/royorel/FFHQ-Aging-Dataset
PROJECT PAGE: http://grail.cs.washington.edu/projects/lifespan_age_transformation_synthesis/ Teaser Video: Lifespan Age Transformation Synthesis](https://i.ytimg.com/vi/_jTFcjN2hBk/mqdefault.jpg)







