Method of reconstrucing 3D color mesh and apparatus for same

1. A method of reconstructing a three-dimensional color mesh, the method comprising:

receiving mesh information of an object, multiple multi-view images obtained by photographing the object at different positions, and camera parameter information corresponding to the multiple multi-view images;

constructing a texture map with respect to the object on the basis of the received information and setting a texture patch referring to a color value of the same multi-view image;

correcting a color value of a vertex included for each texture patch; and

performing rendering with respect to the object by applying the corrected color value of the vertex to the texture map.

2. The method of claim 1 , wherein the correcting of the color value of the vertex comprises:

extracting a boundary vertex included for each texture patch;

calculating a color correction value of the boundary vertex; and

correcting a current color value of the boundary vertex by multiplying the color correction value of the boundary vertex and the current color value of the boundary vertex.

3. The method of claim 2 , wherein the calculating of the color correction value of the boundary vertex comprises:

calculating a target color value of the boundary vertex; and

calculating the color correction value of the boundary vertex by dividing the target color value of the boundary vertex by the current color value of the boundary vertex.

4. The method of claim 3 , wherein the calculating of the color correction value of the boundary vertex comprises:

detecting at least one of the multiple multi-view images, which includes a region corresponding to the boundary vertex;

checking a pixel value of the region corresponding to the boundary vertex from the at least one multi-view image; and

calculating the target color value of the boundary vertex with reference to the checked pixel value of the region corresponding to the boundary vertex.

5. The method of claim 3 , wherein the calculating of the color correction value of the boundary vertex comprises:

detecting at least one of the multiple multi-view images, which includes regions corresponding to the boundary vertexes;

checking pixel values of the regions corresponding to the boundary vertexes from the at least one multi-view image; and

calculating an average value of the checked pixel values of the regions corresponding to the boundary vertexes and calculating the color correction value of the boundary vertex using the calculated average value.

6. The method of claim 2 , wherein the correcting of the color value of the vertex comprises:

extracting an inner vertex included for each texture patch;

calculating a color correction value of the inner vertex; and

correcting a current color value of the inner vertex by multiplying the color correction value of the inner vertex and the current color value of the inner vertex.

7. The method of claim 6 , wherein the calculating of the color correction value of the inner vertex comprises:

checking the color correction value of the boundary vertex included for each texture patch; and

calculating the color correction value of the inner vertex with reference to the color correction value of the boundary vertex.

8. The method of claim 7 , wherein at the calculating of the color correction value of the inner vertex, an average value of the color correction values of the boundary vertexes included for each texture patch is calculated, and the calculated average value is determined as the color correction value of the inner vertex.

9. The method of claim 7 , wherein at the calculating of the color correction value of the inner vertex, the color correction value of the inner vertex is determined to be equal to the color correction value of the boundary vertex included for each texture patch.

10. An apparatus for reconstructing a three-dimensional color mesh, the apparatus comprising:

a processor configured to:

receive mesh information of an object, multiple multi-view images obtained by photographing the object at different positions, and camera parameter information corresponding to the multiple multi-view images so as to construct a texture map with respect to the object;

generate a texture patch including faces referring to a color value of the same multi-view image;

correct a color value of a vertex included for each texture patch; and

perform rendering with respect to the object by applying the corrected color value of the vertex to the texture map.

11. The apparatus of claim 10 , wherein the processor is configured to,

extract a boundary vertex included for each texture patch;

calculate a color correction value of the boundary vertex; and

correct a color value of the boundary vertex by multiplying the color correction value of the boundary vertex and the current color value of the boundary vertex.

12. The apparatus of claim 11 , wherein the processor is configured to,

calculate a target color value of the boundary vertex; and

calculate the color correction value of the boundary vertex by dividing the target color value of the boundary vertex by the current color value of the boundary vertex.

13. The apparatus of claim 11 , wherein the processor is configured to,

extract an inner vertex included for each texture patch;

calculate a color correction value of the inner vertex; and

correct a current color value of the inner vertex by multiplying the color correction value of the inner vertex and the current color value of the inner vertex.

14. The apparatus of claim 13 , wherein the processor is configured to,

check the color correction value of the boundary vertex included for each texture patch, and

calculate the color correction value of the inner vertex with reference to the color correction value of the boundary vertex.