Method and apparatus for training image processing model, and storage medium storing instructions to perform method for training image processing model
There is provided a method for training an image processing model. The method comprises preparing the image processing model including a first generative model, a second generative model, and a segmentation model; inputting a first RGB image into the first generative model and determining a near-infrared ray (NIR) image as an output of the first generative model; inputting the NIR image into the second generative model and determining a second RGB image as an output of the second generative model; inputting the first RGB image and the second RGB image into a segmentation model and determining a first segmentation image and a second segmentation image as outputs of the segmentation model; and setting parameters of the first generative model based on an error between the first RGB image and the second RGB image and an error between the first segmentation image and the second segmentation image.
1 . A method for training an image processing model to be performed by an image processing apparatus including a memory and a processor, the method comprising:
preparing the image processing model including a first generative model, a second generative model, and a segmentation model;
inputting a first RGB image into the first generative model and determining a near-infrared ray (NIR) image as an output of the first generative model;
inputting the NIR image into the second generative model and determining a second RGB image as an output of the second generative model;
inputting the first RGB image and the second RGB image into a segmentation model and determining a first segmentation image and a second segmentation image as outputs of the segmentation model; and
setting parameters of the first generative model based on an error between the first RGB image and the second RGB image and an error between the first segmentation image and the second segmentation image.
2 . The method of claim 1 , wherein the determining of the parameters of the first generative model comprises:
determining parameter values to be applied to the first generative model to minimize the error between the first RGB image and the second RGB image; and
calibrating the determined parameter values to minimize the error between the first segmentation image and the second segmentation image and then applying the calibrated parameter values to the parameters of the first generative model.
3 . An apparatus for training an image processing model, the apparatus comprising:
a memory configured to store a pre-trained image processing model including a first generative model, a second generative model, and a segmentation model, and one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory, wherein the instructions, when executed by the processor, cause the processor to:
input a first RGB image into the first generative model and determine an NIR image as an output of the first generative model;
input the NIR image into the second generative model and determine a second RGB image as an output of the second generative model;
input the first RGB image and the second RGB image into the segmentation model and determine a first segmentation image and a second segmentation image as outputs of the segmentation model; and
set parameters of the first generative model based on an error between the first RGB image and the second RGB image and an error between the first segmentation image and the second segmentation image.
4 . The apparatus of claim 3 , wherein the processor is configured to determine parameter values to be applied to the first generative model to minimize the error between the first RGB image and the second RGB image, calibrate the parameter values to minimize the error between the first segmentation image and the second segmentation image, and apply the calibrated parameter values to the parameters of the first generative model.
5 . A non-transitory computer readable storage medium storing computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method for training an image processing model, the method comprising:
preparing the image processing model including a first generative model, a second generative model, and a segmentation model;
inputting a first RGB image into the first generative model and determining a near-infrared ray (NIR) image as an output of the first generative model;
inputting the NIR image into the second generative model and determining a second RGB image as an output of the second generative model;
inputting the first RGB image and the second RGB image into a segmentation model and determining a first segmentation image and a second segmentation image as outputs of the segmentation model; and
setting parameters of the first generative model based on an error between the first RGB image and the second RGB image and an error between the first segmentation image and the second segmentation image.
6 . The non-transitory computer readable storage medium of claim 5 , wherein the determining of the parameters of the first generative model comprises:
determining parameter values to be applied to the first generative model to minimize the error between the first RGB image and the second RGB image; and
calibrating the determined parameter values to minimize the error between the first segmentation image and the second segmentation image and then applying the calibrated parameter values to the parameters of the first generative model.