Method for synthesizing intermediate view of light field, system for synthesizing intermediate view of light field, and method for compressing light field

1. A method of synthesizing intermediate views of a light field using a specific configuration of an input view of a light field collected by a light field acquiring device and compressing the light field, the method comprising:

selecting a configuration of specific input views of the collected light field;

synthesizing intermediate views of the light field by:

specifying coordinates of intermediate views to be synthesized and inputting the specified coordinates to a neural network and

synthesizing intermediate views, using the neural network, based on a scene disparity, a selected configuration of the specific input views, and the specified coordinates of intermediate views;

calculating a difference between at least one intermediate view and the input view; and

compressing the difference,

wherein the configuration of the specific input views is defined by coordinates of the input view in a light field matrix collected by the light field acquiring device, and

wherein the coordinates of the intermediate views are specified from coordinates in an area surrounded by the coordinates of the input views in the light field matrix.

2. The method of claim 1 , wherein a size of the light field matrix is M×M, M being a positive number, and

the coordinates of the input view correspond to a point included in first and last rows and a point included in first and last columns of the light field matrix having the M×M size.

3. The method of claim 2 , wherein, when the M is an odd number, the point denotes a middle point in the row or column, and

when the M is an even number, the point denotes a point closest to the middle point in the row or column.

4. The method of claim 1 , wherein the coordinates of the intermediate views are expressed by an integer or fraction.

5. The method of claim 1 , further comprising:

calculating a light field feature map based on the selected configuration of specific input views of the light field; and

calculating the scene disparity using the neural network, based on the light field feature map.

6. The method of claim 1 , further comprising previously estimating the scene disparity by using a depth sensor.

7. The method of claim 5 , further comprising synthesizing intermediate views using a pre-trained neural network.

8. A system for synthesizing intermediate views of a light field, the system comprising:

a light field view acquiring device configured to:

capture an input view of a light field scene; and

select a configuration of specific input views of the light field scene;

a first convolutional neural network configured to synthesize intermediate views based on the input view of the light field scene, a scene disparity, and specific coordinates of the intermediate views in a scene light field view array,

wherein the configuration of the specific input views is defined by coordinates of the scene light field view array,

wherein the coordinates of the intermediate views are specified from coordinates in an area surrounded by the coordinates of the input views in the scene light field view array, and

wherein the system is further configured to calculate a difference between at least one intermediate view and the input view, and compress the difference.

9. The system of claim 8 , further comprising:

a first calculation module configured to calculate a light field scene feature map based on the input view of the light field scene;

a second convolutional neural network module configured to calculate a scene disparity based on the light field scene feature map;

a disparity level setting module configured to set a disparity level set of {d1, . . . dL};

a second calculation module configured to calculate a new view with respect to each disparity level using each input view through an equation

wherein denotes a color value of a pixel at a position of coordinates s=(x, y) obtained from N input views pi at a specific disparity level dl; and

a third calculation module configured to calculate from respective generated views, a feature map indicating two characteristics of an average value of color and brightness of the pixel with respect to the disparity level.

10. The system of claim 8 , further comprising a depth sensor configured to provide a depth value used to previously estimate the scene disparity.

11. A mobile device comprising a system for synthesizing intermediate views of a light field, the system performing the method of synthesizing intermediate views of a light field according to claim 1 .