Image processing apparatus performing a deconvolution operation and operation method thereof

1. An image processing apparatus comprising:

a memory storing one or more instructions; and

a processor configured to execute the one or more instructions stored in the memory,

wherein the processor is further configured to execute the one or more instructions to:

divide one or more weights included in a kernel into a plurality of groups based on positions of the one or more weights in the kernel, a size of the kernel, and a size of a stride used in a deconvolution operation, wherein values of the one or more weights are set based on a second image generated by performing the deconvolution operation on a first image;

adjust the values of the one or more weights such that sums of weights respectively included in the plurality of groups are equal to each other; and

generate an output image by performing the deconvolution operation by applying the kernel in which the values of the one or more weights are adjusted to an input image.

2. The image processing apparatus of claim 1 , wherein the processor is further configured to execute the one or more instructions to adjust the values of the one or more weights so that a sum of weights included in each of the plurality of groups is 1.

3. The image processing apparatus of claim 1 , wherein the processor is further configured to execute the one or more instructions to determine a number of the plurality of groups based on the size of the kernel and the size of the stride used in the deconvolution operation.

4. The image processing apparatus of claim 1 , wherein the processor is further configured to execute the one or more instructions to determine a number of the weights included in each of the plurality of groups based on the size of the kernel and the size of the stride used in the deconvolution operation.

5. The image processing apparatus of claim 1 , wherein the processor is further configured to execute the one or more instructions to adjust the values of the weights by applying a reliability map comprising a smoothing function to the kernel.

6. The image processing apparatus of claim 5 , wherein the smoothing function comprises a function of a form in which a value gradually changes based on a center of the reliability map.

7. The image processing apparatus of claim 6 , wherein the smoothing function comprises at least one of a linear function, a Gaussian function, a Laplacian function, or a spline function.

8. The image processing apparatus of claim 1 , wherein a size of the second image is greater than a size of the first image.

9. An operating method of an image processing apparatus, the operating method comprising:

dividing one or more weights included in a kernel into a plurality of groups based on positions of the one or more weights in the kernel a size of the kernel, and a size of a stride used in a deconvolution operation, wherein values of the one or more weights are set based on a second image generated by performing the deconvolution operation on a first image;

adjusting the values of the one or more weights such that sums of weights respectively included in the plurality of groups are equal to each other; and

generating an output image by performing the deconvolution operation by applying the kernel in which the values of the one or more weights are adjusted to an input image.

10. The operating method of claim 9 , wherein the adjusting of the values of the one or more weights comprises adjusting the values of the one or more weights so that a sum of weights included in each of the plurality of groups is 1.

11. The operating method of claim 9 , wherein the dividing one or more weights into the plurality of groups based on the positions of the one or more weights in the kernel comprises determining a number of the plurality of groups based on the size of the kernel and the size of the stride used in the deconvolution operation.

12. The operating method of claim 9 , wherein the dividing one or more weights into the plurality of groups based on the positions of the one or more weights in the kernel comprises determining a number of the weights included in each of the plurality of groups based on the size of the kernel and the size of the stride used in the deconvolution operation.

13. The operating method of claim 9 , wherein the adjusting of the values of the one or more weights comprises adjusting the values of the weights by applying a reliability map comprising a smoothing function to the kernel.

14. The operating method of claim 13 , wherein the smoothing function comprises a function of a form in which a value gradually changes based on a center of the reliability map.

15. The operating method of claim 9 , wherein a size of the second image is greater than a size of the first image.

16. A computer program product comprising one or more non-transitory computer-readable recording media having stored therein a computer program for:

dividing one or more weights included in a kernel into a plurality of groups based on positions of the one or more weights in the kernel, a size of the kernel, and a size of a stride used in a deconvolution operation, wherein values of the one or more weights are set based on a second image generated by performing the deconvolution operation on a first image;

adjusting the values of the one or more weights such that sums of weights respectively included in the plurality of groups are equal to each other; and

generating an output image by performing the deconvolution operation by applying the kernel in which the values of the one or more weights are adjusted to an input image.