Patent
US 11,620,774GENERATIVE ADVERSARIAL NETWORK (GAN)-BASED SYSTEM FOR GENERATING COLOR IMAGE FROM EDGE IMAGE
Won Jun HWANG
US
Copyright © 2026 Matter42. All rights reserved.
Patent
Atlas literature
Patent
US 11,620,774Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram illustrating an example of generating a color image from an edge image; [0016]
FIG. 2 is a diagram for describing an example of a method of operating a generative adversarial network (GAN); [0017]
FIG. 3 is a diagram illustrating an example of a GAN-based system for generating a color image from an edge image; [0018]
FIG. 4 is a diagram for describing an operation of a GAN-based system for generating a color image from an edge image; and [0019]
FIG. 5 is a diagram illustrating an example of a first generator including a first encoder and a first decoder.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
: A generative adversarial network (GAN)-based system for generating a color image from an edge image, the GAN-based system comprising: a first G AN training a model for converting the edge image into at least one intermediate image; and a second G AN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value-ni gner tnan an entropy of the edge image and rres n onds to a value an entropy of the color image, wherein the first G AN includes: a first generator training a model for converting the edge image into the intermediate image; and a first discriminator training a model for discriminating between an image generated by the first generator and a sample image representing the intermediate image, wherein the first generator includes a first encoder including a plurality of convolution layers, wherein the plurality of convolution layers of the first encoder include at least one dilated convolution layer AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ Currently amended
: The GAN-based system of claim 1, wherein the intermediate image corresponds to at least one of a gray image and a luminance component image. Original
: The GAN-based system of claim 1, wherein the first generator further includes: a first decoder including a plurality of deconvolution layers, wherein an intermediate result image generated when the edge image passes through at least one of the plurality of convolution layers in the first encoder is used as an input image of the first decoder. Previously presented
: The GAN-based system of claim 1, wherein the second GAN includes: a second generator training a model for converting the intermediate image into the color image; and AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ a second discriminator training a model for discriminating between an image generated by the second generator and a sample image representing the color image. Original
Canceled
7-13. Canceled
Canceled
Layer stacks claimed or described, ordered top of device to substrate.
GAN-based system for generating a color image from an edge image
Patent
Atlas literature
Patent
US 11,620,774Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram illustrating an example of generating a color image from an edge image; [0016]
FIG. 2 is a diagram for describing an example of a method of operating a generative adversarial network (GAN); [0017]
FIG. 3 is a diagram illustrating an example of a GAN-based system for generating a color image from an edge image; [0018]
FIG. 4 is a diagram for describing an operation of a GAN-based system for generating a color image from an edge image; and [0019]
FIG. 5 is a diagram illustrating an example of a first generator including a first encoder and a first decoder.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
: A generative adversarial network (GAN)-based system for generating a color image from an edge image, the GAN-based system comprising: a first G AN training a model for converting the edge image into at least one intermediate image; and a second G AN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value-ni gner tnan an entropy of the edge image and rres n onds to a value an entropy of the color image, wherein the first G AN includes: a first generator training a model for converting the edge image into the intermediate image; and a first discriminator training a model for discriminating between an image generated by the first generator and a sample image representing the intermediate image, wherein the first generator includes a first encoder including a plurality of convolution layers, wherein the plurality of convolution layers of the first encoder include at least one dilated convolution layer AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ Currently amended
: The GAN-based system of claim 1, wherein the intermediate image corresponds to at least one of a gray image and a luminance component image. Original
: The GAN-based system of claim 1, wherein the first generator further includes: a first decoder including a plurality of deconvolution layers, wherein an intermediate result image generated when the edge image passes through at least one of the plurality of convolution layers in the first encoder is used as an input image of the first decoder. Previously presented
: The GAN-based system of claim 1, wherein the second GAN includes: a second generator training a model for converting the intermediate image into the color image; and AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ a second discriminator training a model for discriminating between an image generated by the second generator and a sample image representing the color image. Original
Canceled
7-13. Canceled
Canceled
Layer stacks claimed or described, ordered top of device to substrate.
GAN-based system for generating a color image from an edge image
Patent
Atlas literature
Patent
US 11,620,774Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram illustrating an example of generating a color image from an edge image; [0016]
FIG. 2 is a diagram for describing an example of a method of operating a generative adversarial network (GAN); [0017]
FIG. 3 is a diagram illustrating an example of a GAN-based system for generating a color image from an edge image; [0018]
FIG. 4 is a diagram for describing an operation of a GAN-based system for generating a color image from an edge image; and [0019]
FIG. 5 is a diagram illustrating an example of a first generator including a first encoder and a first decoder.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
: A generative adversarial network (GAN)-based system for generating a color image from an edge image, the GAN-based system comprising: a first G AN training a model for converting the edge image into at least one intermediate image; and a second G AN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value-ni gner tnan an entropy of the edge image and rres n onds to a value an entropy of the color image, wherein the first G AN includes: a first generator training a model for converting the edge image into the intermediate image; and a first discriminator training a model for discriminating between an image generated by the first generator and a sample image representing the intermediate image, wherein the first generator includes a first encoder including a plurality of convolution layers, wherein the plurality of convolution layers of the first encoder include at least one dilated convolution layer AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ Currently amended
: The GAN-based system of claim 1, wherein the intermediate image corresponds to at least one of a gray image and a luminance component image. Original
: The GAN-based system of claim 1, wherein the first generator further includes: a first decoder including a plurality of deconvolution layers, wherein an intermediate result image generated when the edge image passes through at least one of the plurality of convolution layers in the first encoder is used as an input image of the first decoder. Previously presented
: The GAN-based system of claim 1, wherein the second GAN includes: a second generator training a model for converting the intermediate image into the color image; and AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ a second discriminator training a model for discriminating between an image generated by the second generator and a sample image representing the color image. Original
Canceled
7-13. Canceled
Canceled
Layer stacks claimed or described, ordered top of device to substrate.
GAN-based system for generating a color image from an edge image
Patent
Atlas literature
Patent
US 11,620,774Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram illustrating an example of generating a color image from an edge image; [0016]
FIG. 2 is a diagram for describing an example of a method of operating a generative adversarial network (GAN); [0017]
FIG. 3 is a diagram illustrating an example of a GAN-based system for generating a color image from an edge image; [0018]
FIG. 4 is a diagram for describing an operation of a GAN-based system for generating a color image from an edge image; and [0019]
FIG. 5 is a diagram illustrating an example of a first generator including a first encoder and a first decoder.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
: A generative adversarial network (GAN)-based system for generating a color image from an edge image, the GAN-based system comprising: a first G AN training a model for converting the edge image into at least one intermediate image; and a second G AN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value-ni gner tnan an entropy of the edge image and rres n onds to a value an entropy of the color image, wherein the first G AN includes: a first generator training a model for converting the edge image into the intermediate image; and a first discriminator training a model for discriminating between an image generated by the first generator and a sample image representing the intermediate image, wherein the first generator includes a first encoder including a plurality of convolution layers, wherein the plurality of convolution layers of the first encoder include at least one dilated convolution layer AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ Currently amended
: The GAN-based system of claim 1, wherein the intermediate image corresponds to at least one of a gray image and a luminance component image. Original
: The GAN-based system of claim 1, wherein the first generator further includes: a first decoder including a plurality of deconvolution layers, wherein an intermediate result image generated when the edge image passes through at least one of the plurality of convolution layers in the first encoder is used as an input image of the first decoder. Previously presented
: The GAN-based system of claim 1, wherein the second GAN includes: a second generator training a model for converting the intermediate image into the color image; and AMEN DM ENT UNDER 37 C.F.R. § 1.114(c) Attorney Docket No.: Q₂₅₅₄₄₉ a second discriminator training a model for discriminating between an image generated by the second generator and a sample image representing the color image. Original
Canceled
7-13. Canceled
Canceled
Layer stacks claimed or described, ordered top of device to substrate.
GAN-based system for generating a color image from an edge image