GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
Training a deep-learning gaze estimator requires a massive, diverse, and high-quality training set, which is challenging to produce because it requires photographing subjects and manually labeling pupil position and gaze direction accurately. We'll describe how we created anatomically informed eye and face 3D models for infrared illumination and rendering near-eye images annotated with accurate gaze labels. We use 4M synthetic eye images in combination with real-world images to train a near-eye gaze estimator for VR and AR headsets. Over a wide 40x30-degree field of view, the estimator achieves higher accuracy on real subjects than previous methods. The estimator uses an optimized network architecture that requires fewer convolutional layers than previous deep learning-based gaze trackers, achieving low latency on desktop and mobile hardware. In addition to gaze estimation, we'll show how to use the network for robust pupil estimation and accurate remote-gaze estimation.
Training a deep-learning gaze estimator requires a massive, diverse, and high-quality training set, which is challenging to produce because it requires photographing subjects and manually labeling pupil position and gaze direction accurately. We'll describe how we created anatomically informed eye and face 3D models for infrared illumination and rendering near-eye images annotated with accurate gaze labels. We use 4M synthetic eye images in combination with real-world images to train a near-eye gaze estimator for VR and AR headsets. Over a wide 40x30-degree field of view, the estimator achieves higher accuracy on real subjects than previous methods. The estimator uses an optimized network architecture that requires fewer convolutional layers than previous deep learning-based gaze trackers, achieving low latency on desktop and mobile hardware. In addition to gaze estimation, we'll show how to use the network for robust pupil estimation and accurate remote-gaze estimation.  Back
 
Topics:
Virtual Reality & Augmented Reality, Graphics and AI, AI & Deep Learning Research, Computer Vision
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9571
Streaming:
Download:
Share:
 
Abstract:

Artificial Intelligence has the potential to advance some of the thorniest problems in virtual and augmented reality. Come hear a panel of experts from across the VR industry talk about how deep learning can revolutionize topics ranging from gaze tracking, to user pose sensing and avatar control, to rendering for focus-capable displays, and discuss applications, limitations, and implications of AI in VR.

Artificial Intelligence has the potential to advance some of the thorniest problems in virtual and augmented reality. Come hear a panel of experts from across the VR industry talk about how deep learning can revolutionize topics ranging from gaze tracking, to user pose sensing and avatar control, to rendering for focus-capable displays, and discuss applications, limitations, and implications of AI in VR.

  Back
 
Topics:
Virtual Reality & Augmented Reality
Type:
Panel
Event:
GTC Washington D.C.
Year:
2018
Session ID:
DC8222
Streaming:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next