Generating an alpha channel
A method for generating alpha channel information related to a person, the method may include generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information; wherein the ground-truth alpha channel information is generated by: obtaining input images of the person; wherein each image comprises the person and an arbitrary background; repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color; wherein the first color differs from the second color.
1. A method for generating alpha channel information related to a person, the method comprises:
generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information;
wherein the ground-truth alpha channel information is generated by:
obtaining input images of the person; wherein each image comprises the person and an arbitrary background;
repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color;
wherein the first color differs from the second color;
wherein the training comprises:
repeating, for each input image of the input images:
i. determining person properties within the input image;
ii. generating, by the alpha channel neural network, a first image, the first image is of the first avatar of the person with the first colored background and having the person properties;
iii. comparing first alpha channel information related to the first image to ground-truth alpha channel information related to the first colored background image to provide a first comparison result;
iv. generating, by the alpha channel neural network, a second image, the second image is of the second avatar of the person with the second colored background and having the person properties; and
v. comparing second alpha channel information related to the second image to ground-truth alpha channel information related to the second colored background image to provide a second comparison result.
2. The method according to claim 1 wherein the portrait matting predictor is a matting objective decomposition network.
3. The method according to claim 1 wherein the first color is blue and the second color is green.
4. The method according to claim 1 comprising obtaining images of the person in real time; and wherein the generating comprises generating alpha channel information from the images of the person in real time.
5. The method according to claim 4 wherein the images are obtained during virtual video conferencing.
6. The method according to claim 1 , comprising utilizing the first and second comparison results to update the alpha channel neural network.
7. The method according to claim 1 further comprising generating an avatar of the person.
8. The method according to claim 7 wherein the generating of the avatar of the person comprises utilizing the alpha channel information related to the person.
9. The method according to claim 8 wherein the generating of the avatar of the person comprises generating a three-dimensional model and one or more texture maps of the person.
10. The method according to claim 1 wherein the portrait matting predictor is a robust video matting predictor.
11. A non-transitory computer readable medium for generating alpha channel information related to a person, the non-transitory computer readable medium stores instructions for:
generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information;
wherein the ground-truth alpha channel information is generated by:
obtaining input images of the person; wherein each image comprises the person and an arbitrary background;
repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color;
wherein the first color differs from the second color;
wherein the training comprises:
repeating, for each input image of the input images:
i. determining person properties within the input image;
ii. generating, by the alpha channel neural network, a first image, the first image is of the first avatar of the person with the first colored background and having the person properties;
iii. comparing first alpha channel information related to the first image to ground-truth alpha channel information related to the first colored background image to provide a first comparison result;
iv. generating, by the alpha channel neural network, a second image, the second image is of the second avatar of the person with the second colored background and having the person properties; and
v. comparing second alpha channel information related to the second image to ground-truth alpha channel information related to the second colored background image to provide a second comparison result.
12. The non-transitory computer readable medium according to claim 11 wherein the portrait matting predictor is a matting objective decomposition network.
13. The non-transitory computer readable medium according to claim 11 wherein the first color is blue and the second color is green.
14. The non-transitory computer readable medium according to claim 11 that stores instructions for obtaining images of the person in real time; and wherein the generating comprises generating alpha channel information from the images of the person in real time.
15. The non-transitory computer readable medium according to claim 14 wherein the images are obtained during virtual video conferencing.
16. The non-transitory computer readable medium according to claim 11 that stores instructions for utilizing the first and second comparison results to update the alpha channel neural network.
17. The non-transitory computer readable medium according to claim 11 further that stores instructions for generating an avatar of the person.
18. The non-transitory computer readable medium according to claim 17 wherein the generating of the avatar of the person comprises utilizing the alpha channel information related to the person.
19. The non-transitory computer readable medium according to claim 11 wherein the portrait matting predictor is a robust video matting predictor.
20. A non-transitory computer readable medium for generating alpha channel information related to a person, the non-transitory computer readable medium stores instructions for:
generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information;
wherein the ground-truth alpha channel information is generated by:
obtaining input images of the person; wherein each image comprises the person and an arbitrary background;
repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color;
wherein the first color differs from the second color;
wherein the generating of the avatar of the person comprises utilizing the alpha channel information related to the person; and wherein the generating of the avatar of the person comprises generating a three-dimensional model and one or more texture maps of the person.