Real-time depth-aware image enhancement system

1. A method to enhance a two-dimensional (2D) image, comprising:

performing spatial filtering on the 2D image to generate an edge map;

generating a weighted depth map based on a probability distribution of edges in the edge map;

applying a weighted low-pass filter to the weighted depth map to generate an estimated depth map;

filtering the estimated depth map using a cross-bilateral filter to generate a depth map, wherein the depth map can be used to convert the 2D image to a three-dimensional (3D) image; and

enhancing contrast of the 2D image by

applying a high-pass filter to a first contrast value of a pixel in the 2D image to generate a second contrast value, and

applying a depth value from the depth map and associated with the pixel to the second contrast value.

2. The method as recited in claim 1 , wherein the performing spatial filtering on the 2D image comprises detecting edges in the 2D image based on a defocus depth cue.

3. The method as recited in claim 1 , wherein the enhancing comprises enhancing color of the 2D image.

4. The method as recited in claim 3 , wherein the enhancing color of the 2D image comprises:

determining an ambient light amount for the 2D image;

for a pixel selected from the 2D image, enhancing object light amount of the pixel based on a depth value from the depth map and associated with the pixel; and

adjusting color of the pixel based on the enhanced object light amount and the ambient light amount.

5. The method as recited in claim 4 , wherein the determining the ambient light amount comprises:

identifying a set of pixels in the 2D image that includes low light levels; and

determining the ambient light amount based on light levels associated with the set of pixels.

6. The method as recited in claim 4 , wherein the enhancing the object light amount comprises adjusting the object light amount to enhance depth characteristic associated with the pixel.

7. The method as recited in claim 1 , wherein the method is embodied in a non-transitory machine-readable storage medium as a set of instructions, which in response to execution by a processing unit, cause the processing unit to perform the method.

8. A method to enhance a two-dimensional (2D) video, comprising:

extracting a 2D image from the 2D video;

generating a depth map associated with the 2D image;

de-interlacing the 2D image to generate a de-interlaced 2D image;

performing noise reduction on the de-interlaced 2D image to generate a noise-reduced 2D image;

enhancing contrast of the noise-reduced 2D image to generate a contrast-enhanced 2D image;

enhancing color of the contrast-enhanced 2D image to generate a color-enhanced 2D image using the depth map, wherein the enhancing color includes

identifying a set of pixels in the contrast-enhanced 2D image having low light levels,

determining the ambient light amount based on light levels associated with the set of pixels,

for a pixel selected from the contrast-enhanced 2D image, enhancing object light amount of the pixel based on a depth value from the depth map and associated with the pixel, and

adjusting color of the pixel based on the enhanced object light amount and the ambient light amount;

enhancing sharpness of the color-enhanced 2D image to generate a sharpness-enhanced 2D image; and

scaling the sharpness-enhanced 2D image to generate an enhanced 2D image.

9. The method as recited in claim 8 , wherein the enhancing contrast comprises:

applying a high-pass filter to a first contrast value of a pixel in the noise-reduced 2D image to generate a second contrast value; and

applying a depth value from the depth map and associated with the pixel to the second contrast value.

10. A system configured to enhance a two-dimensional (2D) video, comprising:

a video decoder configured to extract a 2D image from the 2D video;

a depth map generator configured to generate a depth map based on the 2D image, wherein the depth map can be used to convert the 2D image to a three-dimensional (3D) image; and

a video post-processor, coupled with the video decoder and the depth map generator, configured to enhance the 2D image using the depth map, wherein the video post-processor includes

a de-interlacing module configured to de-interlace the 2D image,

a noise-reduction module, coupled with the de-interlacing module, configured to perform noise-reduction on the 2D image,

a scaling module, coupled with the noise-reduction module, configured to scale the 2D image, and

a contrast enhancement module, coupled with the noise-reduction module, configured to enhance contrast of the 2D image using the depth map.

11. The system as recited in claim 10 , wherein the depth map generator comprises an edge detector configured to generate an edge map based on the 2D image.

12. The system as recited in claim 10 , wherein the depth map generator comprises a post-processing filter, coupled with the edge detector, configured to generate the depth map based on the edge map.

13. The system as recited in claim 10 , wherein the video post-processor further comprises:

a color enhancement module, coupled with the contrast enhancement module, configured to enhance color of the 2D image using the depth map.