Stereo matching method and apparatus, image processing apparatus, and training method therefor

1. A stereo matching method, the method comprising:

obtaining a first feature map associated with a first view image and a second feature map associated with a second view image using a neural network model-based feature extractor;

determining respective matching costs between a reference pixel of the first view image and candidate pixels of the second view image using the first feature map and the second feature map; and

determining a pixel corresponding to the reference pixel among the candidate pixels based on the determined matching costs,

wherein the determining of the respective matching costs comprises:

determining an initial matching cost between the reference pixel and a current candidate pixel; and

adjusting the initial matching cost based on matching cost information associated with another reference pixel adjacent to the reference pixel.

2. The stereo matching method of claim 1 , wherein the determining of the pixel comprises determining, to be the pixel corresponding to the reference pixel, a candidate pixel having a lowest matching cost among the candidate pixels.

3. The stereo matching method of claim 1 , wherein the obtaining of the first feature map comprises:

receiving image information of the first view image as an input,

determining a feature vector of the reference pixel based on the input image information, and

obtaining the first feature map based on the feature vector of the reference pixel.

4. The stereo matching method of claim 1 , wherein the obtaining of the second feature map comprises:

receiving image information of the second view image as an input,

determining respective feature vectors of the candidate pixels based on the input image information, and

obtaining the second feature map based on the respective feature vectors of the candidate pixels.

5. The stereo matching method of claim 1 , wherein the obtaining of the first feature map and the second feature map comprises:

obtaining the first feature map based on a patch region of the first view image, and

obtaining the second feature map based on patch regions of the second view image.

6. The stereo matching method of claim 5 , wherein the obtaining of the first feature map comprises:

receiving, as an input, information of a patch region comprising the reference pixel of the first view image,

determining a feature vector of the reference pixel based on the input information of the patch region, and

determining the first feature map based on the feature vector of the reference pixel.

7. The stereo matching method of claim 6 , wherein the information of the patch region comprises any one or any combination of any two or more of intensity information, color information, and gradient information of pixels included in the patch region comprising the reference pixel.

8. The stereo matching method of claim 5 , wherein the obtaining of the second feature map comprises:

receiving, as an input, information of patch regions respectively comprising the candidate pixels of the second view image,

determining respective feature vectors of the candidate pixels based on the input information of the patch regions, and

obtaining the second feature map based on the respective feature vectors of the candidate pixels.

9. The stereo matching method of claim 8 , wherein the information of the patch regions comprises any one or any combination of any two or more of intensity information, color information, and gradient information of pixels included in the patch respectively comprising the candidate pixels.

10. The stereo matching method of claim 1 , wherein the first feature map comprises respective feature vectors of each of pixels included in the first view image, and

the second feature map comprises second feature vectors of each of pixels included in the second view image.

11. The stereo matching method of claim 1 , further comprising determining depth information based on a disparity between the reference pixel and the pixel corresponding to the reference pixel.

12. The method of claim 1 , wherein the determining of the pixel corresponding to the reference pixel comprises determining the pixel corresponding to the reference pixel from a search range of a resultant matching cost volume of the determined respective matching costs.

13. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 .

14. A stereo matching method, the method comprising:

extracting a first feature vector of a reference pixel included in a first view image and respective second feature vectors of each of candidate pixels included in a second view image using a neural network model-based feature extractor; and

determining a pixel corresponding to the reference pixel among the candidate pixels based on the first feature vector and the second feature vectors obtained from the neural network model-based feature extractor, wherein determining comprises:

determining an initial matching cost between the reference pixel and a current candidate pixel;

adjusting the initial matching cost based on matching cost information associated with another reference pixel adjacent to the reference pixel; and

determining the pixel corresponding to the reference pixel among the candidate pixels based on the respective matching costs.

15. An image processing apparatus, comprising:

a processor configured to:

obtain a first feature map associated with a first view image and a second feature map associated with a second view image using a neural network model-based feature extractor;

determine respective matching costs between a reference pixel of the first view image and candidate pixels of the second view image using the first feature map and the second feature map;

determine a pixel corresponding to the reference pixel among the candidate pixels based on the determined matching costs;

determine an initial matching cost between the reference pixel and a current candidate pixel; and

adjust the initial matching cost based on matching cost information associated with another reference pixel adjacent to the reference pixel.

16. The image processing apparatus of claim 15 , wherein the processor is further configured to:

determine, to be the pixel corresponding to the reference pixel, a candidate pixel having a lowest matching cost among the candidate pixels.

17. The image processing apparatus of claim 15 , wherein the processor is further configured to:

receive image information of the first view image as an input,

determine a feature vector of the reference pixel based on the input image information, and

obtain the first feature map based on the feature vector of the reference pixel.

18. The image processing apparatus of claim 15 , wherein the processor is further configured to:

receive image information of the second view image as an input,

determine respective feature vectors of the candidate pixels based on the input image information, and

obtain the second feature map based on the respective feature vectors of the candidate pixels.

19. The image processing apparatus of claim 15 , wherein the processor is further configured to:

obtain the first feature map based on a patch region of the first view image, and

obtain the second feature map based on patch regions of the second view image.

20. The image processing apparatus of claim 19 , wherein the processor is further configured to:

receive as an input, information of a patch region comprising the reference pixel of the first view image,

determine a feature vector of the reference pixel based on the input information of the patch region, and

determine the first feature map based on the feature vector of the reference pixel.