Patent
US 11,972,599 B2METHOD AND APPARATUS FOR GENERATING VEHICLE DAMAGE IMAGE ON THE BASIS OF GAN NETWORK
Juan Xu
Advanced New Technologies Co., Ltd., George Town (KY)·Apr. 30, 2024·US
Copyright © 2026 Matter42. All rights reserved.
Patent
Atlas literature
Patent
US 11,972,599 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates a schematic diagram of a vehicle dam- age image generation system 100 according to an embodi- ment of the present specification;
FIG. 2 illustrates a flowchart of a method for training a discriminative model for vehicle damage images according to an embodiment of the present specification;
FIG. 3 illustrates a flowchart of a method for training an image filling model according to an embodiment of the present specification;
FIG. 4 illustrates a flowchart of a computer-executed method for generating a vehicle damage image according to an embodiment of the present specification;
FIG. 5 illustrates an apparatus 500 for training a discrimi- native model for vehicle damage images according to an embodiment of the present specification;
FIG. 6 illustrates an apparatus 600 for training an image filling model according to an embodiment of the present specification; and
FIG. 7 illustrates a computer-executed apparatus 700 for generating a vehicle damage image according to an embodi- ment of the present specification.
FIG. 8 illustrates an exemplary computer and communi- cation system for generating vehicle damage images accord- ing to one embodiment of the present …
FIG. 9 illustrates an exemplary network environment for implementing the disclosed technology, in accordance with some embodiments described herein.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the real vehicle image includes one or more local images indicating vehicle damage, and wherein label-ing the target box comprises randomly selecting a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The method of claim 1, wherein labeling the target box comprises: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The method of claim 1, wherein removing a portion of the real vehicle image comprises applying a mask, which comprises performing a dot-product operation on the real vehicle image and the mask.
The method of claim 1, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an output image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image gen-erated based on the second real vehicle image.
The method of claim 1, further comprising: using the generated vehicle damage image to train a vehicle damage identification model for identifying damage to a vehicle based on a vehicle damage image.
A computer-executed apparatus for generating a vehicle damage image, comprising: an image-acquisition unit configured to acquire a real vehicle image; an intermediate-image generation unit configured to gen-erate an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and a vehicle-damage-image generation unit configured to generate the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an out-put image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image generated based on the second real vehicle image.
The apparatus of claim 10, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein, while labeling the target box, the intermediate-image generation unit is configured to randomly select a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The apparatus of claim 10, wherein, while labeling the target box, the intermediate-image generation unit is con-figured to: determine, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly select, from the plurality of locations, a location for labeling the target box.
The apparatus of claim 10, wherein, while removing a portion of the real vehicle image, the intermediate-image generation unit is configured to apply a mask on the real vehicle image, which comprises performing a dot-product operation on the real vehicle image and the mask.
The apparatus of claim 10, further comprising a model training unit configured to: obtain a plurality of positive samples and a plurality of negative samples, wherein a respective positive sample is a real image comprising a labeled target box, wherein the target box of the positive sample comprises a local image indicating vehicle damage, wherein the plurality of negative samples comprises a first negative sample being a non-real image comprising a labeled target box, and wherein the first negative sample is obtained by replacing the local image within the target box of a real image with another local image; and use the plurality of positive samples and the plurality of negative samples to train a classification model to be used as the discriminative model.
The apparatus of claim 10, further comprising a 20 second model training unit configured to use the generated vehicle damage image to train a vehicle damage identifica-tion model for identifying damage to a vehicle based on a vehicle damage image.
A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating a vehicle damage image, the method comprising: obtaining a real vehicle image; generating an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into B₂ a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein labeling the target box includes: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high prob-ability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The non-transitory computer-readable storage medium according to claim 19, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein labeling the target box includes randomly selecting a labeling location correspond-ing to one of the one or more local images indicating vehicle damage.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein removing a portion of the real vehicle image includes applying a mask, which includes performing a dot-product operation on the real vehicle image and the mask. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 87
Patent
Atlas literature
Patent
US 11,972,599 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates a schematic diagram of a vehicle dam- age image generation system 100 according to an embodi- ment of the present specification;
FIG. 2 illustrates a flowchart of a method for training a discriminative model for vehicle damage images according to an embodiment of the present specification;
FIG. 3 illustrates a flowchart of a method for training an image filling model according to an embodiment of the present specification;
FIG. 4 illustrates a flowchart of a computer-executed method for generating a vehicle damage image according to an embodiment of the present specification;
FIG. 5 illustrates an apparatus 500 for training a discrimi- native model for vehicle damage images according to an embodiment of the present specification;
FIG. 6 illustrates an apparatus 600 for training an image filling model according to an embodiment of the present specification; and
FIG. 7 illustrates a computer-executed apparatus 700 for generating a vehicle damage image according to an embodi- ment of the present specification.
FIG. 8 illustrates an exemplary computer and communi- cation system for generating vehicle damage images accord- ing to one embodiment of the present …
FIG. 9 illustrates an exemplary network environment for implementing the disclosed technology, in accordance with some embodiments described herein.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the real vehicle image includes one or more local images indicating vehicle damage, and wherein label-ing the target box comprises randomly selecting a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The method of claim 1, wherein labeling the target box comprises: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The method of claim 1, wherein removing a portion of the real vehicle image comprises applying a mask, which comprises performing a dot-product operation on the real vehicle image and the mask.
The method of claim 1, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an output image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image gen-erated based on the second real vehicle image.
The method of claim 1, further comprising: using the generated vehicle damage image to train a vehicle damage identification model for identifying damage to a vehicle based on a vehicle damage image.
A computer-executed apparatus for generating a vehicle damage image, comprising: an image-acquisition unit configured to acquire a real vehicle image; an intermediate-image generation unit configured to gen-erate an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and a vehicle-damage-image generation unit configured to generate the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an out-put image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image generated based on the second real vehicle image.
The apparatus of claim 10, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein, while labeling the target box, the intermediate-image generation unit is configured to randomly select a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The apparatus of claim 10, wherein, while labeling the target box, the intermediate-image generation unit is con-figured to: determine, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly select, from the plurality of locations, a location for labeling the target box.
The apparatus of claim 10, wherein, while removing a portion of the real vehicle image, the intermediate-image generation unit is configured to apply a mask on the real vehicle image, which comprises performing a dot-product operation on the real vehicle image and the mask.
The apparatus of claim 10, further comprising a model training unit configured to: obtain a plurality of positive samples and a plurality of negative samples, wherein a respective positive sample is a real image comprising a labeled target box, wherein the target box of the positive sample comprises a local image indicating vehicle damage, wherein the plurality of negative samples comprises a first negative sample being a non-real image comprising a labeled target box, and wherein the first negative sample is obtained by replacing the local image within the target box of a real image with another local image; and use the plurality of positive samples and the plurality of negative samples to train a classification model to be used as the discriminative model.
The apparatus of claim 10, further comprising a 20 second model training unit configured to use the generated vehicle damage image to train a vehicle damage identifica-tion model for identifying damage to a vehicle based on a vehicle damage image.
A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating a vehicle damage image, the method comprising: obtaining a real vehicle image; generating an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into B₂ a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein labeling the target box includes: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high prob-ability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The non-transitory computer-readable storage medium according to claim 19, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein labeling the target box includes randomly selecting a labeling location correspond-ing to one of the one or more local images indicating vehicle damage.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein removing a portion of the real vehicle image includes applying a mask, which includes performing a dot-product operation on the real vehicle image and the mask. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 87
Patent
Atlas literature
Patent
US 11,972,599 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates a schematic diagram of a vehicle dam- age image generation system 100 according to an embodi- ment of the present specification;
FIG. 2 illustrates a flowchart of a method for training a discriminative model for vehicle damage images according to an embodiment of the present specification;
FIG. 3 illustrates a flowchart of a method for training an image filling model according to an embodiment of the present specification;
FIG. 4 illustrates a flowchart of a computer-executed method for generating a vehicle damage image according to an embodiment of the present specification;
FIG. 5 illustrates an apparatus 500 for training a discrimi- native model for vehicle damage images according to an embodiment of the present specification;
FIG. 6 illustrates an apparatus 600 for training an image filling model according to an embodiment of the present specification; and
FIG. 7 illustrates a computer-executed apparatus 700 for generating a vehicle damage image according to an embodi- ment of the present specification.
FIG. 8 illustrates an exemplary computer and communi- cation system for generating vehicle damage images accord- ing to one embodiment of the present …
FIG. 9 illustrates an exemplary network environment for implementing the disclosed technology, in accordance with some embodiments described herein.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the real vehicle image includes one or more local images indicating vehicle damage, and wherein label-ing the target box comprises randomly selecting a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The method of claim 1, wherein labeling the target box comprises: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The method of claim 1, wherein removing a portion of the real vehicle image comprises applying a mask, which comprises performing a dot-product operation on the real vehicle image and the mask.
The method of claim 1, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an output image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image gen-erated based on the second real vehicle image.
The method of claim 1, further comprising: using the generated vehicle damage image to train a vehicle damage identification model for identifying damage to a vehicle based on a vehicle damage image.
A computer-executed apparatus for generating a vehicle damage image, comprising: an image-acquisition unit configured to acquire a real vehicle image; an intermediate-image generation unit configured to gen-erate an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and a vehicle-damage-image generation unit configured to generate the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an out-put image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image generated based on the second real vehicle image.
The apparatus of claim 10, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein, while labeling the target box, the intermediate-image generation unit is configured to randomly select a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The apparatus of claim 10, wherein, while labeling the target box, the intermediate-image generation unit is con-figured to: determine, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly select, from the plurality of locations, a location for labeling the target box.
The apparatus of claim 10, wherein, while removing a portion of the real vehicle image, the intermediate-image generation unit is configured to apply a mask on the real vehicle image, which comprises performing a dot-product operation on the real vehicle image and the mask.
The apparatus of claim 10, further comprising a model training unit configured to: obtain a plurality of positive samples and a plurality of negative samples, wherein a respective positive sample is a real image comprising a labeled target box, wherein the target box of the positive sample comprises a local image indicating vehicle damage, wherein the plurality of negative samples comprises a first negative sample being a non-real image comprising a labeled target box, and wherein the first negative sample is obtained by replacing the local image within the target box of a real image with another local image; and use the plurality of positive samples and the plurality of negative samples to train a classification model to be used as the discriminative model.
The apparatus of claim 10, further comprising a 20 second model training unit configured to use the generated vehicle damage image to train a vehicle damage identifica-tion model for identifying damage to a vehicle based on a vehicle damage image.
A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating a vehicle damage image, the method comprising: obtaining a real vehicle image; generating an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into B₂ a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein labeling the target box includes: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high prob-ability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The non-transitory computer-readable storage medium according to claim 19, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein labeling the target box includes randomly selecting a labeling location correspond-ing to one of the one or more local images indicating vehicle damage.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein removing a portion of the real vehicle image includes applying a mask, which includes performing a dot-product operation on the real vehicle image and the mask. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 87
Patent
Atlas literature
Patent
US 11,972,599 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates a schematic diagram of a vehicle dam- age image generation system 100 according to an embodi- ment of the present specification;
FIG. 2 illustrates a flowchart of a method for training a discriminative model for vehicle damage images according to an embodiment of the present specification;
FIG. 3 illustrates a flowchart of a method for training an image filling model according to an embodiment of the present specification;
FIG. 4 illustrates a flowchart of a computer-executed method for generating a vehicle damage image according to an embodiment of the present specification;
FIG. 5 illustrates an apparatus 500 for training a discrimi- native model for vehicle damage images according to an embodiment of the present specification;
FIG. 6 illustrates an apparatus 600 for training an image filling model according to an embodiment of the present specification; and
FIG. 7 illustrates a computer-executed apparatus 700 for generating a vehicle damage image according to an embodi- ment of the present specification.
FIG. 8 illustrates an exemplary computer and communi- cation system for generating vehicle damage images accord- ing to one embodiment of the present …
FIG. 9 illustrates an exemplary network environment for implementing the disclosed technology, in accordance with some embodiments described herein.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the real vehicle image includes one or more local images indicating vehicle damage, and wherein label-ing the target box comprises randomly selecting a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The method of claim 1, wherein labeling the target box comprises: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The method of claim 1, wherein removing a portion of the real vehicle image comprises applying a mask, which comprises performing a dot-product operation on the real vehicle image and the mask.
The method of claim 1, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an output image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image gen-erated based on the second real vehicle image.
The method of claim 1, further comprising: using the generated vehicle damage image to train a vehicle damage identification model for identifying damage to a vehicle based on a vehicle damage image.
A computer-executed apparatus for generating a vehicle damage image, comprising: an image-acquisition unit configured to acquire a real vehicle image; an intermediate-image generation unit configured to gen-erate an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and a vehicle-damage-image generation unit configured to generate the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein the machine-learning model is a generative model in a Generative Adversarial Network (GAN) model, wherein the GAN model further comprises a discriminative model for determining whether an out-put image of the generative model is a real image and whether a local image indicating vehicle damage is in the target box of the output image, and wherein the generative model is trained based on the discriminative model, a second real vehicle image, and a second intermediate image generated based on the second real vehicle image.
The apparatus of claim 10, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein, while labeling the target box, the intermediate-image generation unit is configured to randomly select a labeling location corresponding to one of the one or more local images indicating vehicle damage.
The apparatus of claim 10, wherein, while labeling the target box, the intermediate-image generation unit is con-figured to: determine, based on statistics, a plurality of locations at which vehicle damage occurs with a high probability; and randomly select, from the plurality of locations, a location for labeling the target box.
The apparatus of claim 10, wherein, while removing a portion of the real vehicle image, the intermediate-image generation unit is configured to apply a mask on the real vehicle image, which comprises performing a dot-product operation on the real vehicle image and the mask.
The apparatus of claim 10, further comprising a model training unit configured to: obtain a plurality of positive samples and a plurality of negative samples, wherein a respective positive sample is a real image comprising a labeled target box, wherein the target box of the positive sample comprises a local image indicating vehicle damage, wherein the plurality of negative samples comprises a first negative sample being a non-real image comprising a labeled target box, and wherein the first negative sample is obtained by replacing the local image within the target box of a real image with another local image; and use the plurality of positive samples and the plurality of negative samples to train a classification model to be used as the discriminative model.
The apparatus of claim 10, further comprising a 20 second model training unit configured to use the generated vehicle damage image to train a vehicle damage identifica-tion model for identifying damage to a vehicle based on a vehicle damage image.
A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating a vehicle damage image, the method comprising: obtaining a real vehicle image; generating an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into B₂ a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein labeling the target box includes: determining, based on statistics, a plurality of locations at which vehicle damage occurs with a high prob-ability; and randomly selecting, from the plurality of locations, a location for labeling the target box.
The non-transitory computer-readable storage medium according to claim 19, wherein the real vehicle image comprises one or more local images indicating vehicle damage, and wherein labeling the target box includes randomly selecting a labeling location correspond-ing to one of the one or more local images indicating vehicle damage.
A computer-executed method for generating a vehicle damage image, comprising: obtaining a real vehicle image; generating, by a computer, an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box; and generating the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image, wherein removing a portion of the real vehicle image includes applying a mask, which includes performing a dot-product operation on the real vehicle image and the mask. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 87
Cited non-patent literature · 2
Cited non-patent literature · 2
Cited non-patent literature · 2
Cited non-patent literature · 2