System and method of cross-modulated dense local fusion for few-shot image generation
US12100082B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 9, 2022 |
| Grant date | Sep 24, 2024 |
| Priority date | — |
| Expiry date | Apr 11, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2200/24
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.