FIELD: data processing.
SUBSTANCE: invention relates to image processing. Method of training an image generation model, comprising: obtaining a first transformation model through training, wherein the first transformation model is configured to generate a first training image based on the first noise sample, and the first training image is a first style image, obtaining a reconstruction model by training based on the first transformation model, obtaining a second transformation model by training, wherein the second transformation model is configured to generate a second training image based on the second noise sample, and the second training image is a second style image, generating a spliced transformation model by splicing the first transformation model with a second transformation model and creating an image generation model based on the reconstruction model and the spliced transformation model.
EFFECT: wider range of tools for image generation.
15 cl, 10 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| IMAGE PROCESSING METHOD, AN IMAGE PROCESSING DEVICE AND A DATA MEDIUM | 2018 |
|
RU2709437C1 |
| IMAGE GENERATORS WITH CONDITIONALLY INDEPENDENT PIXEL SYNTHESIS | 2021 |
|
RU2770132C1 |
| METHOD AND SERVER FOR WAVEFORM GENERATION | 2021 |
|
RU2803488C2 |
| METHOD FOR LOCAL GENERATION AND REPRESENTATION OF WALLPAPER STREAM AND COMPUTER IMPLEMENTING IT | 2020 |
|
RU2768551C1 |
| MODELLING PEOPLE'S CLOTHING BASED ON MULTIPLE POINTS | 2021 |
|
RU2776825C1 |
| METHODS AND SYSTEMS FOR IMAGE PROCESSING | 2016 |
|
RU2705014C1 |
| METHODS AND SYSTEMS FOR IMAGE PROCESSING | 2016 |
|
RU2797310C2 |
| IMAGING SYSTEM | 2006 |
|
RU2343458C2 |
| NEURAL NETWORK FOR GENERATING SYNTHETIC MEDICAL IMAGES | 2017 |
|
RU2698997C1 |
| METHOD OF GENERATING A COMMON LOSS FUNCTION FOR TRAINING A CONVOLUTIONAL NEURAL NETWORK FOR CONVERTING AN IMAGE INTO AN IMAGE WITH DRAWN PARTS AND A SYSTEM FOR CONVERTING AN IMAGE INTO AN IMAGE WITH DRAWN PARTS | 2019 |
|
RU2706891C1 |
