Restoration filter for truncated pixels

• US 5,699,079 A
• Filed: 11/21/1995
• Issued: 12/16/1997
• Est. Priority Date: 11/21/1995
• Status: Expired due to Term

• Current Assignee: RPX Corporation
• Original Assignee: Silicon Graphics Incorporated (Graphics Properties Holdings, Inc.)
• Inventors: Gossett, Carroll Philip
• Primary Examiner(s): Tung, Kee M.
• Application Number:
  US08/561,584
• Time in Patent Office: 756 Days
• Field of Search: 395/162-166, 395/501, 395/502, 395/503, 395/507, 395/515, 345/133, 345/136, 345/138, 345/139, 345/147, 345/185, 345/189, 345/153, 345/155, 348/671, 358/429, 358/443, 358/448, 358/455-460, 382/260-262, 382/274, 382/254, 382/258
• US Class Current: 345/605
• CPC Class Codes: G06T 5/20 using local operators

Abstract

A system and method for restoring bits of pixels prior to display where the original bits of the pixels were truncated compares each pixel to its neighbors to determine the relative value of each pixel as compared to its neighbors. First, the truncated pixel is shifted. That is, the remaining bits of the pixel are shifted to the left and additional bits are added in the least significant bit positions. Next, the pixel is compared to its neighbors to determine their relative values. For each neighbor that is greater than the pixel in question, the truncated shifted pixel is incremented by one. Similarly, for each neighbor that is less than the pixel in question, the truncated shifted pixel is decremented by one. Once the pixel is evaluated relative to its neighboring pixels, determination of the restored pixel is complete. The restored pixel can then be displayed.

Claims

1. In a computer graphics system having a graphics processor for computing a pixel to be displayed and a frame buffer for storing a truncated portion of the pixel to be displayed, a method for restoring the pixel to be displayed prior to display, the method comprising the steps of:

shifting the truncated portion of the pixel to be displayed to the left by one or more bits thereby creating a truncated shifted pixel;

comparing the truncated portion of the pixel to be displayed to a neighboring pixel of the pixel to be displayed;

incrementing said truncated shifted pixel where a value of said neighboring pixel is greater than a value of the pixel to be displayed; and

decrementing said truncated shifted pixel where a value of said neighboring pixel is less than a value of the pixel to be displayed.

2. The method according to claim 1, wherein said steps of comparing, incrementing and decrementing are performed for each neighboring pixel of said pixel to be displayed.

3. In a computer graphics system having a graphics processor and a frame buffer for storing a truncated portion of a pixel to be displayed, a method for restoring the pixel to its full complement of bits prior to display, the method comprising the steps of:

comparing the truncated portion of the pixel to be displayed to a neighboring pixel;

determining a value of a restored offset portion of the pixel to be displayed based on results of said step of comparing; and

appending said restored offset portion to said truncated portion of the pixel to be displayed to restore the pixel to be displayed.

4. The method of claim 3, further comprising the step of repeating said steps of comparing and determining for each pixel neighboring the pixel to be restored.

5. The method of claim 4, wherein said step of determining a value of a restored offset portion of the pixel to be displayed comprises the steps of:

incrementing said restored offset portion of the pixel to be displayed for each compared neighboring pixel that has a value greater than the pixel to be displayed; and

decrementing said restored offset portion of the pixel to be displayed for each compared neighboring pixel that has a value less than the pixel to be displayed.

6. In a computer graphics system having a processor for generating pixels to be displayed and having a frame buffer for storing the pixels generated by the processor, a method for reducing a number of bits required to be stored in the frame buffer to represent a pixel while maintaining image quality, the method comprising the steps of:

truncating the bits representing the pixel to be displayed to remove a subset of the bits and leave a truncated portion of the pixel to be displayed;

storing said truncated portion of the pixel to be displayed in the frame buffer;

comparing said truncated portion of the pixel to be displayed to at least one neighboring pixel; and

modifying the pixel to be displayed based on said comparison to restore the pixel prior to display.

7. The method of claim 6, wherein said modifying step comprises the steps of:

shifting said truncated portion of the pixel to be displayed to the left by one or more bits prior to said comparing step thereby creating a truncated Shifted pixel;

incrementing said truncated Shifted pixel where said neighboring pixel is greater than said truncated portion of the pixel to be displayed; and

decrementing said truncated shifted pixel where said neighboring pixel is less than said truncated portion of the pixel to be displayed.

8. The method of claim 7, further comprising the step of repeating said steps of truncating, storing, shifting, comparing, incrementing and decrementing for each pixel to be displayed.

9. The method according to claim 7, wherein said steps of comparing, incrementing and decrementing for a pixel to be restored are performed for each pixel that is a neighboring pixel of said pixel to be displayed.

10. The method of claim 7, further comprising the step of dithering the bits representing a pixel prior to truncation.

11. The method according to claim 6, wherein said modifying step comprises the steps of:

determining a value of a restored offset portion based on results of said step of comparing; and

appending said restored offset portion to said truncated portion of the pixel to be displayed prior to display.

12. The method of claim 11, further comprising the step of repeating said steps of truncating, storing, comparing, determining and appending for each pixel to be displayed.

13. In a system for displaying an image using pixels the system having a memory for storing the pixels, a method for reducing a number of bits required to be stored in memory for each pixel while maintaining image quality, the method comprising the steps of:

truncating the bits for at least one of the pixels to be displayed to remove a subset of the bits and leave a truncated portion for each truncated pixel;

storing said truncated portion of each truncated pixel in the memory;

comparing said truncated portion of each truncated pixel to at least one neighboring pixel; and

modifying said truncated pixels based on said comparing step to restore said truncated pixels prior to display.

14. The method of claim 13, wherein said modifying step comprises:

shifting said truncated portion to the left by one or more bits prior to said comparing step thereby creating a truncated Shifted pixel;

incrementing said truncated shifted pixel where said neighboring pixel is greater than the truncated portion of the pixel to be displayed; and

decrementing said truncated shifted pixel where said neighboring pixel is less than the truncated portion of the pixel to be displayed.

15. The method of claim 14, further comprising the step of repeating said steps of shifting, comparing, incrementing and decrementing for each pixel to be restored.

16. The method according to claim 14, wherein said steps of comparing, incrementing and decrementing for a pixel to be restored are performed for each neighboring pixel.

17. The method according to claim 13, wherein said modifying step comprises the steps of:

determining a value of a restored offset portion of said truncated pixel based on results of said step of comparing; and

appending said restored offset portion to said truncated portion to restore the pixel to be displayed.

18. The method according to claim 17, further comprising the step of repeating said steps of comparing, determining and appending for each pixel to be restored.

19. The method of claim 13, further comprising the step of dithering the bits of the pixel prior to truncation.

20. A computer program product for use with a computer system, said computer program product comprising:

a computer usable medium having computer readable program code means embodied in said medium for causing the computer system to generate pixels to be displayed, to store the pixels generated by the processor in memory, and to reduce the number of bits required to be stored in the memory to represent each pixel while maintaining image quality, said computer readable program code means comprising

computer readable program code means for truncating the bits representing said pixel to be displayed to remove a subset of the bits and leave a truncated portion for said pixel,

computer readable program code means for storing, in memory, said truncated portion of the pixel to be displayed,

computer readable program code means for comparing said truncated portion to a neighboring pixel, and

computer readable program code means for modifying said pixel to be displayed based on said comparison to restore said pixel to be displayed prior to display.

21. The computer program product according to claim 20, wherein said computer readable program code means for modifying said pixel to be displayed comprises:

computer readable program code means for shifting said truncated portion of the pixel to be displayed to the left by one or more bits prior to said comparison to create a truncated shifted pixel;

computer readable program code means for incrementing said truncated shifted pixel where said neighboring pixel is greater than said truncated portion; and

computer readable program code means for decrementing said truncated shifted pixel where said neighboring pixel is less than said truncated portion.

22. The computer program product according to claim 21, further comprising:

computer readable program code means for repeating said means for truncating, storing, shifting, comparing, incrementing and decrementing for each pixel to be displayed; and

computer readable program code means for comparing, incrementing and decrementing each pixel to be restored for each neighboring pixel.

23. The computer program product according to claim 20, wherein said computer readable program code means for modifying said pixel to be displayed comprises:

computer readable program code means for determining a value of a restored offset portion of said pixel to be displayed based on results of said comparison; and

computer readable program code means for appending said restored offset portion to said truncated portion prior to display.

24. The computer program product according to claim 23, further comprising:

computer readable program code means for causing said computer system to repeat said truncating, storing, comparing, determining and appending for each pixel to be displayed.