Low dynamic range 3-channel color compression

• US 7,983,498 B1
• Filed: 08/06/2007
• Issued: 07/19/2011
• Est. Priority Date: 08/06/2007
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Donovan, Walter E.
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): YEH, EUENG NAN
• Application Number:
  US11/834,624
• Time in Patent Office: 1,443 Days
• Field of Search: 382/232, 382/235, 375/240
• US Class Current: 382/235
• CPC Class Codes: H03M 7/40 Conversion to or from variable length codes, e.g. Shannon-Fano code, Huffman code, Morse code
• CPC Class Codes: H04N 1/41 Bandwidth or redundancy reduction by scanning H04N1/17 ; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00
• CPC Class Codes: H04N 1/642 Adapting to different types of images, e.g. characters, graphs, black and white image portions
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object
• CPC Class Codes: H04N 19/46 Embedding additional information in the video signal during the compression process H04N19/517, H04N19/68, H04N19/70 take precedence
• CPC Class Codes: H04N 19/91 Entropy coding, e.g. variable length coding [VLC] or arithmetic coding

Abstract

Systems and methods for representing low dynamic range data in compressed formats with a fixed size block allow low dynamic range data to be stored in less memory. The compressed formats use 8 bits per pixel to represent 24 bits of low dynamic range data for each pixel. The compressed format includes four or six endpoint values, a partition index that specifies a mask for each pair of the endpoint values, and an index for each pixel in the block. The indices are compressed to allow more bits for the endpoint values. Mode bits are included to distinguish between the different encodings and various blocks within a single compressed image may be encoded differently. Compressed low dynamic range values may be efficiently decompressed in hardware.

Claims

1. A method of compressing low dynamic range data into a compressed format, comprising:

determining a partitioning of pixels into regions to produce a partition index for a fixed size block of low dynamic range data;

determining a first reference endpoint and remaining endpoints to produce an endpoint pair for each region of the fixed size block;

determining a variable length mode that indicates a number of bits used to represent each endpoint and a number of the regions;

computing a second compressed endpoint, a third compressed endpoint, and a fourth compressed endpoint when the remaining endpoints are encoded as differences;

determining compressed indices corresponding to the pixels within the fixed size block of low dynamic range data, wherein each compressed index specifies a low dynamic range value for one channel of a single pixel of the pixels; and

encoding the variable length mode, the partition index, the compressed indices, the first reference endpoint, and the compressed endpoints to produce the low dynamic range data in the compressed format.

2. The method of claim 1, further comprising the step of computing a fifth compressed endpoint and a sixth compressed endpoint when the number of regions is three.

3. The method of claim 1, wherein the step of determining the compressed indices comprises removing a most significant bit from one index of each endpoint pair based on the partition index and the partitioning of the pixels.

4. The method of claim 1, wherein the step of computing the second compressed endpoint and the third compressed endpoint comprises subtracting the reference endpoint channel values from the second endpoint channel values and subtracting the reference endpoint channel values from the third endpoint channel values.

5. The method of claim 4, wherein the step of computing the fourth compressed endpoint comprises subtracting the reference endpoint channel values from the fourth endpoint channel values.

6. The method of claim 1, wherein the step of computing the fifth compressed endpoint and the sixth compressed endpoint comprises subtracting the reference endpoint channel values from the fifth endpoint channel values and subtracting the reference endpoint channel values from the sixth endpoint channel values.

7. The method of claim 1, wherein the partitioning of the pixels divides the pixels into two or three regions of the fixed size block.

8. The method of claim 1, wherein each channel of the low dynamic range data is quantized to a number of bits specified for each possible compressed endpoint field of variable length prior to being compressed.

9. The method of claim 1, further comprising storing the low dynamic range data represented in the compressed format in a memory.

10. A non-transitory computer-readable medium containing instructions for controlling a computer system to compress low dynamic range data into a compressed format, comprising:

determining a partitioning of pixels in a fixed size block of low dynamic range data;

determining a first reference endpoint and remaining endpoints to produce an endpoint pair for each partition of the fixed size block;

determining a variable length mode that indicates a number of bits used to represent each endpoint and a number of partitions;

computing a second compressed endpoint, a third compressed endpoint, and a fourth compressed endpoint when the remaining endpoints are encoded as differences;

determining compressed indices corresponding to the pixels within the fixed size block of low dynamic range data, wherein each compressed index specifies a low dynamic range value for one channel of a single pixel; and

encoding the variable length mode, the compressed indices, the first reference endpoint, and the compressed endpoints to produce the low dynamic range data in the compressed format.

11. A compressed data format representing low dynamic range data embodied in a non-transitory computer-readable medium, the compressed data format comprising:

a first field of variable length including mode bits that indicate whether the compressed data format specifies that the low dynamic range data is encoded using a four point transform or a six point transform;

a second field of variable length including a partition index that specifies a partition mask indicating a pair of decompressed endpoints that is used to compute a decompressed low dynamic range values for each channel of each pixel;

a compressed endpoint field of variable length including four compressed endpoints or six compressed endpoints; and

an index field of variable length including compressed indices that each correspond to pixels within a fixed size block of low dynamic range data, wherein each of the compressed indices is used to compute a decompressed low dynamic range value for one channel of a single pixel of the pixels.

12. The compressed data format of claim 11, wherein the endpoint compression format specifies a reference endpoint of the four compressed endpoints or the six compressed endpoints and whether remaining compressed endpoints are encoded as differences or are uncompressed.

13. The compressed data format of claim 12, wherein three compressed endpoints of the four compressed endpoints are differences relative to the reference endpoint.

14. The compressed data format of claim 12, wherein five compressed endpoints of the six compressed endpoints are differences relative to the reference endpoint.

15. The compressed data format of claim 11, wherein the endpoint compression format specifies a number of bits for each channel of the four compressed endpoints or the six compressed endpoints in the compressed endpoint field.

16. The compressed data format of claim 11, wherein a bit of a compressed index for each pair of decompressed endpoints is encoded by the mode bits and the partition mask.

17. The compressed data format of claim 11, wherein the partition mask includes an identifier for each of the pixels in the fixed size block to indicate a first portion of the pixels in the fixed size block that are compressed using a first pair of the six compressed endpoints, a second portion of the pixels in the fixed size block that are compressed using a second pair of the six compressed endpoints, and a remaining portion of the pixels in the fixed size block that are compressed using a third pair of the six compressed endpoints when the endpoint compression mode indicates that the six point transform is used to encode the low dynamic range data.

18. The compressed data format of claim 11, wherein the partition mask includes an identifier for each of the pixels in the fixed size block to indicate a first portion of the pixels in the fixed size block that are compressed using a first pair of the four compressed endpoints and a remaining portion of the pixels in the fixed size block that are compressed using a second pair of the four compressed endpoints when the endpoint compression mode indicates that the six point transform is not used to encode the low dynamic range data.

19. The compressed data format of claim 11, wherein each channel of the low dynamic range data is quantized to a number of bits specified for each possible compressed endpoint field of variable length prior to being compressed.