Method and device for image generation and colorization
AssigneePing An Technology (Shenzhen) Co., Ltd.
InventorsYuchuan Gou, Minghao Li, Bo Gong, Mei Han
Life of this patent
Estimating the term…
Abstract
A method for image generation and colorization includes displaying a drawing board interface; obtaining semantic labels of an image to be generated based on user input on the drawing board interface, each semantic label indicating a content of a region in the image to be generated; obtaining a color feature of the image to be generated; and automatically generating the image using a generative adversarial network (GAN) model according to the semantic labels and the color feature. The color feature is a latent vector input to the GAN model.
Claims18
A method for image generation and colorization, applied to a computing device, comprising:
- displaying a drawing board interface;
- obtaining semantic labels of an image to be generated based on user input on the drawing board interface, each semantic label indicating a content of a region in the image to be generated;
- obtaining a color feature of the image to be generated, wherein obtaining the color feature comprises obtaining a stroke image having a same size as the image to be generated, the stroke image including one or more colored strokes input by a user, and extracting the color feature based on the stroke image;
- and
- automatically generating the image using a generative adversarial network (GAN) model according to the semantic labels and the color feature, the color feature being a latent vector input to the GAN model.
A device for image generation and colorization, comprising:
- a memory;
- and
- a processor coupled to the memory and configured to perform:
- displaying a drawing board interface;
- obtaining semantic labels of an image to be generated based on user input on the drawing board interface, each semantic label indicating a content of a region in the image to be generated;
- obtaining a color feature of the image to be generated, wherein obtaining the color feature comprises obtaining a stroke image having a same size as the image to be generated, the stroke image including one or more colored strokes input by a user, and extracting the color feature based on the stroke image;
- and
- automatically generating the image using a generative adversarial network (GAN) model according to the semantic labels and the color feature, the color feature being a latent vector input to the GAN model.
A non-transitory computer readable storage medium, storing computer instructions that, when being executed by a processor, causing the processor to perform:
- displaying a drawing board interface;
- obtaining semantic labels of an image to be generated based on user input on the drawing board interface, each semantic label indicating a content of a region in the image to be generated, wherein obtaining the color feature comprises obtaining a stroke image having a same size as the image to be generated, the stroke image including one or more colored strokes input by a user, and extracting the color feature based on the stroke image;
- obtaining a color feature of the image to be generated;
- and
- automatically generating the image using a generative adversarial network (GAN) model according to the semantic labels and the color feature, the color feature being a latent vector input to the GAN model.
Dependencies are inferred from the claim text.