System and method for restoration of dynamic range of images and video

1. A method, comprising:

receiving, by a processor from an upstream device, a D-dimensional vector data set of media content, wherein D is greater than or equal to one;

applying, by a processor, a low-frequency-pass method to the received D-dimensional vector data set of media content to generate a low-frequency D-dimensional vector data set of media content;

obtaining, by the processor, a structure tensor field comprising a set of D-dimensional structure tensors corresponding to each vector of the received D-dimensional vector data set of media content;

performing, by the processor, an eigensystem analysis for each structure tensor in the field of structure tensors to generate a plurality of D eigenvalue fields comprising D eigenvalues for each vector of the received D-dimensional vector data set of media content;

interpolating, by the processor, between each vector of the received D-dimensional vector data set of media content and a corresponding vector from the low-frequency D-dimensional vector data set of media content in view of one or more of the D eigenvalues for each vector of the plurality of D eigenvalue fields to produce a restored-dynamic range D-dimensional vector data set of media content; and

outputting, by the processor, the restored-dynamic range D-dimensional vector data set of media content to a display or downstream device.

2. The method of claim 1 , wherein applying a low-frequency-pass method to the received D-dimensional vector data set of media content comprises:

generating a D-dimensional Gaussian pyramid from the received D-dimensional vector data set of media content; and

selecting D-dimensional vector data from the lowest dimension pyramid level of the D-dimensional Gaussian pyramid to generate the low-frequency D-dimensional vector data set of media content.

3. The method of claim 1 , wherein obtaining a set of D-dimensional structure tensors comprises computing a set of D-dimensional directional gradients for each vector of the received D-dimensional vector data set of media content.

4. The method of claim 1 , wherein obtaining a set of D-dimensional structure tensors comprises performing a structure tensor analysis with one element of each vector of the received D-dimensional vector data set of media content.

5. The method of claim 1 , wherein interpolating comprises linearly interpolating between each vector of the received D-dimensional vector data set of media content and the corresponding vector from the low-frequency D-dimensional vector data set of media content.

6. The method of claim 1 , wherein interpolating comprises:

generating a Gaussian pyramid from each of the plurality of D eigenvalue fields;

employing one or more of the D eigenvalues to assign linear weights to each vector of the lowest resolution plurality of D eigenvalue fields; and

employing the linear weights to interpolate between each vector of the received D-dimensional vector data set of media content and the corresponding vector from the low-frequency D-dimensional vector data set of media to produce the restored-dynamic range D-dimensional vector data set of media content.

7. The method of claim 6 , wherein the linear weights are assigned in view of a region-of-support used for obtaining the structure tensor field.

8. The method of claim 6 , wherein employing one or more of the D eigenvalues to assign linear weights to each vector of the lowest resolution plurality of D eigenvalue fields comprises:

selecting an eigenvalue of the D eigenvalues indicative of a homogenous region of support about a vector of the received D-dimensional vector data as the lower bound for assigning the linear weights; and

selecting one of the remaining eigenvalues of the D eigenvalues indicative of an edge or highly textured region of support about a vector of the received D-dimensional vector data as the upper bound for assigning the linear weights.

9. The method of claim 1 , wherein interpolating comprises performing an interpolation jointly between all element of each vector of the received D-dimensional vector data set and the corresponding elements of each vector from the low-frequency D-dimensional vector data set.

10. The method of claim 1 , wherein said applying a low-frequency-pass method and said interpolating are performed in parallel.

11. The method of claim 1 , wherein the media content comprises at least one of audio, one or more two-dimensional still images, one or more three-dimensional still images, two-dimensional video, three-dimensional video, magnetic resonance imaging (MRI) data, computed tomography (CT)-scan data, geometric data, seismic data, holographic data, or meteorological data.

12. The method of claim 1 , wherein each vector of the received D-dimensional vector data set of media content, the low-frequency D-dimensional vector data set of media content, and the restored-dynamic range D-dimensional vector data set of media content comprises N-dimensional scalar values where N is equal to or greater than 1.

13. The method of claim 1 , wherein the received D-dimensional vector data set of media content, the low-frequency D-dimensional vector data set of media content, and the restored-dynamic range D-dimensional vector data set of media content each comprise D-dimensional pixel values.

14. The method of claim 13 , wherein the pixel values comprise color values or luminance values or both color values and luminance values.

15. A system, comprising:

a memory;

a processing device coupled to and having use of the memory, the processing device to:

receive, from an upstream device, a D-dimensional vector data set of media content, wherein D is greater than or equal to one;

apply a low-frequency-pass method to the received D-dimensional vector data set of media content to generate a low-frequency D-dimensional vector data set of media content;

obtain a structure tensor field comprising a set of D-dimensional structure tensors corresponding to each vector of the received D-dimensional vector data set of media content;

perform an eigensystem analysis for each structure tensor in the field of structure tensors to generate a plurality of D eigenvalue fields comprising D eigenvalues for each vector of the received D-dimensional vector data set of media content;

interpolate between each vector of the received D-dimensional vector data set of media content and a corresponding vector from the low-frequency D-dimensional vector data set of media content in view of one or more of the D eigenvalues for each vector of the plurality of D eigenvalue fields to produce a restored-dynamic range D-dimensional vector data set of media content; and

output the restored-dynamic range D-dimensional vector data set of media content to a display or downstream device.

16. The system of claim 15 , wherein applying a low-frequency-pass method to the received D-dimensional vector data set of media content comprises:

generating a D-dimensional Gaussian pyramid from the received D-dimensional vector data set of media content; and

selecting D-dimensional vector data from the lowest dimension pyramid level of the D-dimensional Gaussian pyramid to generate the low-frequency D-dimensional vector data set of media content.

17. The system of claim 15 , wherein obtaining a set of D-dimensional structure tensors comprises computing a set of D-dimensional directional gradients for each vector of the received D-dimensional vector data set of media content.

18. The system of claim 15 , wherein obtaining a set of D-dimensional structure tensors comprises performing a structure tensor analysis with one element of each vector of the received D-dimensional vector data set of media content.

19. The system of claim 15 , wherein interpolating comprises:

generating a Gaussian pyramid from each of the plurality of D eigenvalue fields;

employing one or more of the D eigenvalues to assign linear weights to each vector of the lowest resolution plurality of D eigenvalue fields; and

employing the linear weights to interpolate between each vector of the received D-dimensional vector data set of media content and the corresponding vector from the low-frequency D-dimensional vector data set of media to produce the restored-dynamic range D-dimensional vector data set of media content.

20. A non-transitory computer-readable storage medium including instructions that, when accessed by a processing device, cause the processing device to perform operations comprising:

receiving, by the processing device from an upstream device, a D-dimensional vector data set of media content, wherein D is greater than or equal to one;

applying, by the processing device, a low-frequency-pass method to the received D-dimensional vector data set of media content to generate a low-frequency D-dimensional vector data set of media content;

obtaining, by the processing device, a structure tensor field comprising a set of D-dimensional structure tensors corresponding to each vector of the received D-dimensional vector data set of media content;

performing, by the processing device, an eigensystem analysis for each structure tensor in the field of structure tensors to generate a plurality of D eigenvalue fields comprising D eigenvalues for each vector of the received D-dimensional vector data set of media content;

interpolating, by the processing device, between each vector of the received D-dimensional vector data set of media content and a corresponding vector from the low-frequency D-dimensional vector data set of media content in view of one or more of the D eigenvalues for each vector of the plurality of D eigenvalue fields to produce a restored-dynamic range D-dimensional vector data set of media content; and

outputting, by the processing device, the restored-dynamic range D-dimensional vector data set of media content to a display or downstream device.

21. The non-transitory computer-readable storage medium of claim 20 , wherein applying a low-frequency-pass method to the received D-dimensional vector data set of media content comprises:

generating a D-dimensional Gaussian pyramid from the received D-dimensional vector data set of media content; and

selecting D-dimensional vector data from the lowest dimension pyramid level of the D-dimensional Gaussian pyramid to generate the low-frequency D-dimensional vector data set of media content.

22. The non-transitory computer-readable storage medium of claim 20 , wherein obtaining a set of D-dimensional structure tensors comprises computing a set of D-dimensional directional gradients for each vector of the received D-dimensional vector data set of media content.

23. The non-transitory computer-readable storage medium of claim 20 , wherein obtaining a set of D-dimensional structure tensors comprises performing a structure tensor analysis with one element of each vector of the received D-dimensional vector data set of media content.

24. The non-transitory computer-readable storage medium of claim 20 , wherein interpolating comprises:

generating a Gaussian pyramid from each of the plurality of D eigenvalue fields;

employing one or more of the D eigenvalues to assign linear weights to each vector of the lowest resolution plurality of D eigenvalue fields; and

employing the linear weights to interpolate between each vector of the received D-dimensional vector data set of media content and the corresponding vector from the low-frequency D-dimensional vector data set of media to produce the restored-dynamic range D-dimensional vector data set of media content.