Systems for digital image compression using context-based pixel predictor selection

In a digital medium environment for compressing digital images, a system comprising:

• a grouping module implemented at least partially in hardware of a computing device to:
• receive digital image data describing pixels of a digital image;
• and
• group first differences between values of the pixels and first prediction values of the pixels into context groups;
• a prediction module implemented at least partially in the hardware of the computing device to:
• determine a pixel predictor for each of the context groups based on a compression criterion;
• and
• generate second prediction values of the pixels using the determined pixel predictor for pixels corresponding to the first differences included in each of the context groups;
• a regrouping module implemented at least partially in the hardware of the computing device to group second differences between the values of the pixels and the second prediction values of the pixels into different context groups;
• and
• an entropy coding module implemented at least partially in the hardware of the computing device to compress the digital image using entropy coding based on the different context groups.

One or more computer-readable storage media comprising instructions stored thereon that, responsive to execution by a computing device, causes the computing device to perform operations including:

• receiving digital image data describing pixels of a digital image;
• generating first prediction values of the pixels;
• grouping first differences between values of the pixels and the first prediction values of the pixels into context groups;
• determining a pixel predictor for each of the context groups based on a compression criterion;
• generating second prediction values of the pixels using the determined pixel predictor for pixels corresponding to the first differences included in each of the context groups;
• and
• grouping second differences between the values of the pixels and the second prediction values of the pixels into different context groups.