Using boundary maps to refine imagery
Various approaches to image enhancement are disclosed. In one approach, an image to be enhanced and a boundary map are received. A field value array is made using the boundary map and the received image. For each field represented in the field value array, pixel values obtained from the received image are aggregated. An enhanced image is generated as output by performing a rereasterization using the aggregated values. In another approach, an image to be enhanced and an edge map are received. Edge-masked derivative matrices are constructed. The edge-masked derivative matrices are used to iteratively solve a series of linear equations, wherein solutions to the linear equations minimize an increasingly accurate quadratic approximation of a penalty function that measures a total amount of variation in a function, and a derivation of the function from the image. A vector result of the iterative solution is transformed into a raster image.
1. A system, comprising:
a processor configured to:
receive an image to be enhanced and a boundary map;
make a field value array using the boundary map and the received image, wherein making the field value array includes iterating over pixels obtained from the received image, and appending a first pixel's data to a first field;
aggregate, for each field represented in the field value array, pixel values obtained from the received image; and
generate as output an enhanced version of the received image by performing a rasterization using the aggregated pixel values; and
a memory coupled to the processor and configured to provide the processor with instructions.
2. The system of claim 1 wherein the received image includes a plurality of blank pixels and wherein the enhanced version of the received image in-paints at least some of the blank pixels.
3. The system of claim 1 wherein the received image has a first resolution, and wherein, as a result of performing the rasterization using the aggregated pixel values, the enhanced version of the received image has a second resolution that is higher than the first resolution.
4. The system of claim 3 wherein the second resolution is a resolution of the boundary map.
5. The system of claim 1 wherein the received image has a first amount of noise, and wherein, as a result of performing the rasterization using the aggregated pixel values, the enhanced version of the received image has an amount of noise that is reduced from the received image.
6. A method, comprising:
receiving an image to be enhanced and a boundary map;
making a field value array using the boundary map and the received image, wherein making the field value array includes iterating over pixels obtained from the received image, and appending a first pixel's data to a first field;
aggregating, for each field represented in the field value array, pixel values obtained from the received image; and
generating as output an enhanced version of the received image by performing a rasterization using the aggregated pixel values.
7. The method of claim 6 wherein the received image includes a plurality of blank pixels and wherein the enhanced version of the received image in-paints at least some of the blank pixels.
8. The method of claim 6 wherein the received image has a first resolution, and wherein, as a result of performing the rasterization using the aggregated pixel values, the enhanced version of the received image has a second resolution that is higher than the first resolution.
9. The method of claim 8 wherein the second resolution is a resolution of the boundary map.
10. The method of claim 6 wherein the received image has a first amount of noise, and wherein, as a result of performing the rasterization using the aggregated pixel values, the enhanced version of the received image has an amount of noise that is reduced from the received image.
11. The system of claim 1 wherein aggregating pixel values includes determining a mean pixel value for the first field.
12. The system of claim 1 wherein aggregating pixel values includes determining a median pixel value for the first field.
13. The system of claim 1 wherein aggregating pixel values includes determining a mode pixel value for the first field.
14. The system of claim 1 wherein aggregating pixel values includes excluding NaN pixel values.
15. The system of claim 1 wherein the received image comprises multi-spectral data and wherein aggregating the pixel values includes separately aggregating, for a given field, pixel values corresponding to each spectrum.
16. The system of claim 1 wherein the boundary map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.
17. The method of claim 6 wherein aggregating pixel values includes determining a mean pixel value for the first field.
18. The method of claim 6 wherein aggregating pixel values includes determining a median pixel value for the first field.
19. The method of claim 6 wherein aggregating pixel values includes determining a mode pixel value for the first field.
20. The method of claim 6 wherein aggregating pixel values includes excluding NaN pixel values.
21. The method of claim 6 wherein the received image comprises multi-spectral data and wherein aggregating the pixel values includes separately aggregating, for a given field, pixel values corresponding to each spectrum.
22. The method of claim 6 wherein the boundary map comprises a plurality of fields and wherein each field included in the plurality of fields has a unique identifier.