View synthesis using deep convolutional neural networks
US10846836B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 14, 2016 |
| Grant date | Nov 24, 2020 |
| Priority date | — |
| Expiry date | Apr 17, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20228
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed is a system and method for generating intermediate views between two received images. To generate the intermediate views, a rectification network rectifies the two images and an encoder network encodes the two rectified images to generate convolutional neural network features. The convolutional neural network features are fed to a decoder network that decodes the features to generate a correspondence between the two rectified images and blending masks to predict the visibility of pixels of the rectified images in the intermediate view images. Using the correspondence between the two rectified images and blending masks, a view morphing network synthesizes intermediate view images depicting an object in the two images in a view between the two images.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.