Image processing method and apparatus

1. An image processing method comprising:

obtaining, by an image processing apparatus, points on left-eye and right-eye images to be generated from a two-dimensional (2D) image, to which a predetermined pixel of the 2D image is to be mapped, using sizes of holes to be generated in the left-eye and right-eye images; and

generating, by the image processing apparatus, the left-eye and right-eye images respectively having the obtained points to which the predetermined pixel of the 2D image is mapped.

2. The image processing method as claimed in claim 1 , wherein the obtaining of the points comprises obtaining the points such that an average size of one or more holes in the generated left-eye image and an average size of one or more holes in the generated right-eye image are equal to each other.

3. The image processing method as claimed in claim 1 , wherein the obtaining of the points comprises determining the sizes of the holes using a depth value to be applied to the 2D image.

4. The image processing method as claimed in claim 3 , wherein the determining of the sizes of the holes comprises:

dividing the 2D image into a plurality of blocks;

obtaining a depth value difference between neighboring blocks by using depth values of the neighboring blocks; and

determining the sizes of the holes using the depth value difference.

5. The image processing method as claimed in claim 1 , wherein the obtaining of the points comprises:

obtaining the point on the left-eye image according to Xl′=x−(1−a)*Shift_x; and obtaining the point on the right-eye image according to Xr′=x+(1+a)*Shift_x,

where X′ is a location value of the point on the left-eye image, Xr′ is a location value of the point on the right-eye image, x is a location value of the predetermined pixel on the 2D image, Shift_x is a value corresponding to a shift of the predetermined pixel from x in the left-eye and right-eye images, and a is a value in a range from −1 to 1 corresponding to the sizes of the holes to be generated.

6. The image processing method as claimed in claim 5 , wherein a is obtained from meta data corresponding to the 2D image.

7. The image processing method as claimed in claim 1 , wherein the holes correspond to absent portions of an object and/or a background in the generated left-eye and right-eye images that are respectively visible on the object when actually viewed from image observation points respectively corresponding to a left-eye and a right eye of which the left-eye and right-eye images are based, the portions being absent in the generated left-eye and right-eye images.

8. An image processing apparatus comprising:

a position calculator to obtain points on left-eye and right-eye images to be generated from a two-dimensional (2D) image, to which a predetermined pixel of the 2D image is to be mapped, using sizes of holes to be generated in the left-eye and right-eye images; and

a stereo rendering unit to generate the left-eye and right-eye images respectively having the obtained points to which the predetermined pixel of the 2D image is mapped.

9. The image processing apparatus as claimed in claim 8 , wherein the position calculator determines the sizes of the holes using a depth value to be applied to the 2D image.

10. The image processing apparatus as claimed in claim 9 , wherein the position calculator divides the 2D image into a plurality of blocks, obtains a depth value difference between neighboring blocks by using depth values of the neighboring blocks, and determines the sizes of the holes by using the depth value difference.

11. The image processing apparatus as claimed in claim 8 , wherein the position calculator obtains the point on the left-eye image according to Xl′=x−(1−a)*Shift_x, and obtains the point on the right-eye image according to Xr′=x+(1+a)*Shift_x, wherein Xl′ is a location value of the point on the left-eye image, Xr′ is a location value of the point on the right-eye image, x is a location value of the predetermined pixel on the 2D image, Shift_x is a value corresponding to a shift of the predetermined pixel from x in the left-eye and right-eye images, and a is a value in a range from −1 to 1 corresponding to the sizes of the holes to be generated.

12. A non-transitory computer readable recording medium encoded with computer instructions for executing the method of claim 1 and implemented by the image processing apparatus.