Methods and apparatus to detect a region of interest based on variable rate shading

1 . An apparatus comprising:

at least one memory;

machine readable instructions; and

at least one processor circuit to be programmed based on the machine readable instructions to:

partition a variable rate shaded (VRS) mask of a video image into divisions, the VRS mask generated by renderer circuitry, the divisions of the VRS mask having pixels;

assign weights to the pixels based on corresponding variable rate shadings provided in the VRS mask;

sum the weights of the pixels of respective ones of the divisions of the VRS mask to determine respective total weights for the divisions;

identify ones of the divisions of the VRS mask having total weights that satisfy a threshold as important divisions;

detect one or more regions of interest of the video image based on the important divisions of the VRS mask; and

encode the one or more regions of interest of the video image.

2 . The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to:

reduce a size of the VRS mask to create a map;

label components of the map that are connected to one another and associated with the important divisions;

generate a boundary around ones of the components that are labeled; and

identify the boundary as associated with a candidate region of interest.

3 . The apparatus of claim 2 , wherein one or more of the at least one processor circuit is to:

determine an effectivity value associated with the boundary;

generate a score associated with the boundary based on the effectivity value; and

supply the boundary as a region of interest to an encoder.

4 . The apparatus of claim 1 , wherein one or more of the at least one processor circuit is to:

reduce a size of the VRS mask;

identify one or more groups of pixels included in the VRS mask that are associated with important divisions and that touch one another;

select a subset of the one or more groups of pixels based on effectivity values associated respectively with the one or more groups of pixels;

calculate scores for the one or more groups of pixels in the subset; and

select, from among the subset, the one or more of the regions of interest to be identified to an encoder.

5 . A non-transitory machine readable storage medium comprising instructions to cause at least one processor circuit to at least:

detect that a variable rate shading (VRS) mask associated with a video image includes potential regions of interest;

reduce a size of the VRS mask to create a map;

identify a set of connected components of the map having components that are connected together and associated with weights that satisfy a threshold;

generate a boundary around the set of the connected components;

detect one or more regions of interest of the video image based on the boundary; and

encode the one or more detected regions of interest of the video image.

6 . The non-transitory machine readable storage medium of claim 5 , wherein the weights are total weights, and the instructions are to cause one or more of the at least one processor circuit to:

divide the VRS mask of the video image into divisions, the divisions including respective pixels;

assign respective weights to ones of the pixels based on variable shading rates of the respective pixels;

determine, for each of the divisions, sums of the respective weights of the pixels included in the divisions to obtain the total weights for the divisions; and

identify ones of the divisions of the VRS mask having total weights that satisfy the threshold as being the potential regions of interest.

7 . The non-transitory machine readable storage medium of claim 5 , wherein the instructions are to cause one or more of the at least one processor circuit to:

determine boundaries around respective sets of connected components having components that are connected together and associated with weights that satisfy the threshold;

determine respective effectivity values for the boundaries;

determine respective final scores for the boundaries based on the effectivity values; and

select one or more of the boundaries based on the final scores to form the one or more detected regions of interest.

8 . A method comprising:

identifying respective sets of connected components of a variable rate shading (VRS) map, the sets of connected components having components that are connected together and associated with weights that satisfy a threshold, the VRS map based on a VRS mask associated with a video image;

determining boundaries around the respective sets of the connected components;

determining respective effectivity scores for the boundaries;

determining respective final scores for the boundaries based on the effectivity scores;

selecting, based on the final scores, one or more of the boundaries to form regions of interest of the video image; and

encoding, with at least one processor circuit, the regions of interest of the video image.

9 . The method of claim 8 , including:

dividing the VRS mask of the video image into sub-components, the sub-components including pixels;

assigning respective weights to the pixels based on variable shading rates of the pixels identified in the VRS mask;

determining sums of the respective weights associated with the sub-components to determine respective total weights for the sub-components; and

based on the total weights of the sub-components, identifying the VRS mask of the video image as having region of interest candidates.

10 . The method of claim 8 , including reducing a size of the VRS mask to create the VRS map.

11 . The apparatus of claim 1 , wherein one of more of the at least one processor circuit is to:

adjust a quantization parameter based on a first region of interest of the one or more regions of interest; and

encode the first region of interest of the video image based on the adjusted quantization parameter.

12 . The non-transitory machine readable storage medium of claim 5 , wherein the instructions are to cause one or more of the at least one processor circuit to:

adjust a quantization parameter based on a first region of interest of the one or more regions of interest; and

encode the first region of interest of the video image based on the adjusted quantization parameter.

13 . The method of claim 8 , including:

adjusting a quantization parameter based on a first region of interest of the regions of interest; and

encoding the first region of interest of the video image based on the adjusted quantization parameter.