Method and system for improved image compression

Abstract

A system configured to perform pre-processing on a plurality of frames representative of an image, such as frames of a video sequences, to improve the compressibility of the video sequence during video encoding. In some cases, the plurality of frames are utilized to generate a deblocked image that may be compressed by the video encoder to further improve compression rates with respect to the original video sequence.

What is claimed is: 
     
         1 . A method comprising:
 receive a first plane associated with original image data, the first plane including a first plurality of pixels corresponding to a first set of pixels of the original image data;   receive a second plane associated with the original image data, the second plane including a second plurality of pixels corresponding to second set of pixels of the original image data;   generating a deblocked image from the first plane and the second plane; and   compressing the deblocked image.   
     
     
         2 . The method as recited in  claim 1 , further comprising pre-processing the original image data to generate the first plane and the second plane. 
     
     
         3 . The method as recited in  claim 1 , further comprising:
 receiving a third plane, the third plane including a third portion of the original image data;   receiving a fourth plane, the fourth plane including a fourth portion of the original image data; and   wherein the deblocked image includes data from the third plane and the fourth plane.   
     
     
         4 . The method as recited in  claim 1 , further comprising applying at least one deblocking filter to the first plane and the second plane. 
     
     
         5 . The method as recited in  claim 1 , wherein generating the deblocked image includes applying a weight at least one pixel of individual ones of the one or more planes. 
     
     
         6 . The method as recited in  claim 5 , wherein generating the deblocked image includes applying a weight to one or more pixels of a first plane of the one or more planes based on a distance of the one or more pixels from a center of the first plane. 
     
     
         7 . The method as recited in  claim 1 , wherein generating the deblocked image includes generating the deblocked image from data associated with pixels position proximate to a center of each of the one or more planes. 
     
     
         8 . The method as recited in  claim 1 , wherein:
 generating the deblocked image includes weighting pixels of individual ones of the one or more planes; and   a sum of the weight of the pixels at a given position relative to the image data within the individual ones of the one or more planes is equal to one.   
     
     
         9 . One or more non-transitory computer-readable media having computer-executable instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 receive, at a deblocking component, a first plane and a second plane associated with original image data, wherein the first plane includes a first plurality of pixels corresponding to a first set of pixels of the original image data and the second plane includes a second plurality of pixels corresponding to second set of pixels of the original image data; and   generating, at the deblocking component, a deblocked image from the first plane and the second plane; and   compressing, by an encoder component, the deblocked image.   
     
     
         10 . The one or more non-transitory computer-readable media as recited in  claim 1 , wherein the original image data is at least one of an image, a frame of a video sequence, or frames of a video sequence. 
     
     
         11 . The one or more non-transitory computer-readable media as recited in  claim 1 , wherein generating the deblocked image data includes applying a weight at least one pixel of the individual one of the one or more of planes. 
     
     
         12 . The one or more non-transitory computer-readable media as recited in  claim 11 , wherein the weight is based on a distance of the at least one pixel from a center of a block associated with at least one of the one or more of planes. 
     
     
         13 . The one or more non-transitory computer-readable media as recited in  claim 11 , wherein the at least one pixel contributes data to the deblocked image data based at least in part on the weight. 
     
     
         14 . A system comprising:
 a deblocking unit, the deblocking unit to:
 receive a first plane and a second plane associated with original image data, wherein the first plane includes a first plurality of pixels corresponding to a first set of pixels of the original image data and the second plane includes a second plurality of pixels corresponding to second set of pixels of the original image data; and 
 generate a deblocked image from the first plane and the second plane; and 
   an encoder to compress the deblocked image.   
     
     
         15 . The system as recited in  claim 14 , further comprising a pre-processor to process the original image data and generate the first plane and the second plane. 
     
     
         16 . The dimensional processor as recited in  claim 14 , wherein:
 the deblocking unit receives a third plane and a fourth plane, the third plane includes a third portion of the original image data and the fourth plane includes a fourth portion of the original image data; and   the deblocked image includes data from the third plane and the fourth plane.   
     
     
         17 . The dimensional processor as recited in  claim 14 , wherein the first set of pixels is different than the second set of pixels. 
     
     
         18 . The dimensional processor as recited in  claim 14 , wherein the first set of pixels includes at least one pixel of the second set of pixels. 
     
     
         19 . The dimensional processor as recited in  claim 15 , further comprising:
 weighting the first plurality of pixels of the first plane and the second plurality of pixels of the second plane, a first pixel of the first plurality of pixels having a first weight, a second pixel of the second plurality of pixels having a second weight, the first pixel and the second pixel having a corresponding position relative to the original image data; and   wherein generating the deblocked image includes generating a third pixel of the deblocked image based at least in part on the first pixel, the second pixel, the first weight, and the second weight.   
     
     
         20 . The dimensional processor as recited in  claim 19 , wherein the first weight is based at least in part on a distance of the first pixel from a center of the first plane.