Techniques to use a neural network to expand an image
US12340484B2 · kind B2 · utility
0Cited by
0References
4Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 9, 2020 |
| Grant date | Jun 24, 2025 |
| Priority date | — |
| Expiry date | Jan 26, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.