No
Yes
View More
View Less
Working...
Close
OK
Cancel
Confirm
System Message
Delete
Schedule
An unknown error has occurred and your request could not be completed. Please contact support.
Scheduled
Wait Listed
Personal Calendar
Speaking
Conference Event
Meeting
Interest
Schedule TBD
Conflict Found
This session is already scheduled at another time. Would you like to...
Loading...
Please enter a maximum of {0} characters.
Please enter a maximum of {0} words.
must be 50 characters or less.
must be 40 characters or less.
Session Summary
We were unable to load the map image.
This has not yet been assigned to a map.
Search Catalog
Reply
Replies ()
Search
New Post
Microblog
Microblog Thread
Post Reply
Post
Your session timed out.
This web page is not optimized for viewing on a mobile device. Visit this site in a desktop browser to access the full set of features.
2017 GTC San Jose

S7710 - Novel 3D View Synthesis from a Single Image

Session Speakers
Session Description

In this session, we will learn how deep convolutional networks can be trained to synthesize novel 3D views of an object from a single image. We will start with problem background in vision, graphics and robotics and review state-of-the-art approaches using either deep learning or geometry. We then will introduce our method by grounding an image generation network on learnable 3D geometric transformations, and present results on renderings of 3D object models and real images with applications to 3D object reconstruction and 3D photo editing.


Additional Session Information
All
Talk
Computer Vision and Machine Vision Deep Learning and AI
Media & Entertainment
25 minutes
Session Schedule