Three-dimensionalization method and apparatus for two-dimensional image, device and computer-readable storage medium

A three-dimensionalization apparatus for a two-dimensional image, comprising:

• a memory, configured to store executable instructions;
• and
• a processor, configured to, when executing the executable instruction stored in the memory, perform:
• performing depth perception processing on a two-dimensional (2D) image, to obtain depth values of a plurality of pixels in the two-dimensional image;
• performing migration processing on the two-dimensional image from multiple perspectives, to obtain a migration result of the two-dimensional image corresponding to each perspective;
• determining color values of pixels in a migration image corresponding to each perspective, based on the depth values of the pixels in the two-dimensional image and the migration result of the two-dimensional image corresponding to each perspective;
• generating, based on the color values of the pixels in the migration image of each perspective, the migration image corresponding to the perspective;
• and
• encapsulating the migration images of the multiple perspectives in an order, to obtain a three-dimensional video,
• wherein the migration processing on the 2D image for each perspective comprises:
• for a pixel in the plurality of pixels in the 2D image:
• determining a horizontal motion vector based on a motion sensitive parameter, a horizontal motion parameter corresponding to the perspective, a depth value of the pixel in the 2D image, and a width of the 2D image;
• determining a vertical motion vector based on the motion sensitive parameter, a vertical motion parameter corresponding to the perspective, the depth value of the pixel, and a height of the 2D image;
• and
• obtaining an original position where the pixel in the 2D image is located in a migration image canvas of the perspective, and performing displacement processing with the original position as a starting point and according to the horizontal motion vector and the vertical motion vector, to obtain a migration position where the pixel in the 2D image is located in the migration image canvas.

A non-transitory computer-readable storage medium, storing an executable instruction, the executable instruction, when executed by at least one processor, causing the at least one processor to perform:

• performing depth perception processing on a two-dimensional (2D) image, to obtain a depth values of a plurality of pixels in the two-dimensional image;
• performing migration processing on the two-dimensional image from multiple perspectives, to obtain a migration result of the two-dimensional image corresponding to each perspective;
• determining color values of pixels in a migration image corresponding to each perspective, based on the depth values of the pixels in the two-dimensional image and the migration result of the two-dimensional image corresponding to each perspective;
• generating, based on the color values of the pixels in the migration image of each perspective, the migration image corresponding to the perspective;
• and
• encapsulating the migration images of the multiple perspectives in an order, to obtain a three-dimensional video,
• wherein the migration processing on the 2D image for each perspective comprises:
• for a pixel in the plurality of pixels in the 2D image:
• determining a horizontal motion vector based on a motion sensitive parameter, a horizontal motion parameter corresponding to the perspective, a depth value of the pixel in the 2D image, and a width of the 2D image;
• determining a vertical motion vector based on the motion sensitive parameter, a vertical motion parameter corresponding to the perspective, the depth value of the pixel, and a height of the 2D image;
• and
• obtaining an original position where the pixel in the 2D image is located in a migration image canvas of the perspective, and performing displacement processing with the original position as a starting point and according to the horizontal motion vector and the vertical motion vector, to obtain a migration position where the pixel in the 2D image is located in the migration image canvas.