Method for storing interpolation data

Abstract

A method for storing interpolation data is provided, which includes the following steps: dividing a buffer into a plurality of regions, and using the regions to store the interpolation data of a plurality of non-integer points. The decimal part of each logical coordinate for each of the non-integer points is identical to that of the corresponding logical coordinate for another of the non-integer points in the same region.

What is claimed is: 
     
         1 . A method for storing interpolation data, comprising:
 dividing a buffer into a plurality of regions; and   using the regions to store the interpolation data of a plurality of non-integer points;   wherein, the decimal part of each logical coordinate for each of the non-integer points is identical to that of the corresponding logical coordinate for another of the non-integer points in the same region.   
     
     
         2 . The method for storing interpolation data as claimed in  claim 1 , wherein the collection of the decimal parts of each logical coordinate for each of the non-integer points is different from that of the decimal parts of each logical coordinate for another of the non-integer points in a different region. 
     
     
         3 . The method for storing interpolation data as claimed in  claim 1 , wherein the method for storing interpolation data is applied to video encoding or video decoding. 
     
     
         4 . The method for storing interpolation data as claimed in  claim 3 , further comprising:
 counting the size distribution of MVDs of at least one video bitstream; and   determining the size of the buffer according to the size distribution.   
     
     
         5 . A method for storing interpolation data, comprising:
 dividing a buffer into a plurality of regions;   using the regions to store the interpolation data of a plurality of non-integer points, wherein the decimal part of each logical coordinate for each of the non-integer points is identical to that of each logical coordinate for another of the non-integer points in the same region;   if the interpolation data of a specific non-integer point is stored in the buffer, providing the interpolation data directly; and   if the interpolation data of the specific non-integer point is not stored in the buffer, reading the data of a plurality of integer points adjacent to the specific non-integer point from a memory, calculating the interpolation data based on the data of the integer points, and storing the interpolation data into the buffer.   
     
     
         6 . The method for storing interpolation data as claimed in  claim 5 , wherein the collection of the decimal parts of each logical coordinate for each of the non-integer points is different from that of the decimal parts of each logical coordinate for another of the non-integer points in a different region. 
     
     
         7 . The method for storing interpolation data as claimed in  claim 5 , further comprising:
 if the specific non-integer point exceeds the boundary of the buffer, adjusting the logical coordinates of the starting point of the buffer, so as to make the specific non-integer point fall within the boundary of the buffer.   
     
     
         8 . The method for storing interpolation data as claimed in  claim 7 , further comprising:
 for each logical coordinate of the specific non-integer point, calculating the result of the logical coordinate minus the corresponding logical coordinate of the starting point plus the corresponding real coordinate of the starting point, wherein the result is taken as the real coordinate corresponding to the logical coordinate of the specific non-integer point;   if the real coordinate of the specific non-integer point is smaller than the corresponding lower limit of the buffer, adding the corresponding side length of the buffer to the real coordinate;   if the real coordinate of the specific non-integer point is larger than the corresponding upper limit of the buffer, subtracting the corresponding side length of the buffer from the real coordinate; and   accessing the buffer with the real coordinates of the specific non-integer point.   
     
     
         9 . The method for storing interpolation data as claimed in  claim 5 , wherein the method for storing interpolation data is implemented by a calculation system, the buffer is stored in a cache memory of the calculation system, and the memory storing the data of the integer points is an external memory of the calculation system. 
     
     
         10 . The method for storing interpolation data as claimed in  claim 9 , wherein the calculation system is a video encoder or video decoder, and the method for storing the interpolation data further comprises:
 counting the size distribution of MVDs of at least one video bitstream; and   determining the size of the buffer according to the size distribution.