| CPC G06T 7/11 (2017.01) [G06F 40/40 (2020.01); G06T 5/70 (2024.01); G06T 7/50 (2017.01); G06T 2210/12 (2013.01)] | 23 Claims |
|
21. A system, comprising:
a processor programmed to:
access an input image;
generate a plurality of segments based on one or more segmentation models and the input image, each segment from among the plurality of segments representing a corresponding salient object;
generate a depth map based on a depth estimation model;
layer the plurality of segments, based on the depth map and border regions between pairs of segments, to generate a plurality of ordered segments, wherein to layer the plurality of segments, the processor is programmed to:
generate a pairwise depth ordering of the plurality of segments that considers only the border region between each pair of segments and provides a relative ordering of segments in each pair with respect to one another; and
perform global topological sorting based on the pairwise depth ordering, wherein the respective depth value of each is based on the global topological sorting; and
execute a vision-language model to generate a text annotation of the image based on the plurality of ordered segments.
|