Patent · US Active

Model training method, media information synthesis method, and related apparatuses

US12283087B2 · kind B2 · utility

0Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 1, 2020
Grant dateApr 22, 2025
Priority date
Expiry dateFeb 21, 2044

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04N5/265
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

A model training method includes obtaining an image sample set and brief-prompt information; generating a content mask set according to the image sample set and the brief-prompt information; generating a to-be-trained image set according to the content mask set; obtaining, based on the image sample set and the to-be-trained image set, a predicted image set through a to-be-trained information synthesis model, the predicted image set comprising at least one predicted image, the predicted image being in correspondence to the image sample; and training, based on the predicted image set and the image sample set, the to-be-trained information synthesis model by using a target loss function, to obtain an information synthesis model.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.