Shallow depth of field (SDOF) rendering

An electronic device, comprising:

• one or more image capture devices;
• one or more processors;
• and
• a memory coupled to the one or more processors, wherein instructions are stored in the memory, and wherein the instructions, when executed, cause the one or more processors to:
• obtain a first image of a scene, the first image comprising a first plurality of pixels;
• obtain a set of initial focus information for the first image;
• create a defocus map for the first image based, at least in part, on the obtained set of initial focus information;
• obtain at least one segmentation mask comprising a first plurality of segmentation values, wherein each segmentation value corresponds to a location in the scene;
• refine the defocus map, wherein refining the defocus map is based, at least in part, on the first plurality of segmentation values;
• generate an initial depth map based, at least in part, on the refined defocus map;
• generate a refined depth map based, at least in part, on a combination of the generated initial depth map and the obtained at least one segmentation mask;
• and
• generate a blurred version of the first image based, at least in part, on the refined depth map.

An image processing method, comprising:

• obtaining a first image of a scene, the first image comprising a first plurality of pixels;
• obtaining a set of initial focus information for the first image;
• creating a defocus map for the first image based, at least in part, on the obtained set of initial focus information;
• obtaining at least one segmentation mask comprising a first plurality of segmentation values, wherein each segmentation value corresponds to a location in the scene;
• refining the defocus map, wherein refining the defocus map is based, at least in part, on the first plurality of segmentation values;
• generating an initial depth map based, at least in part, on the refined defocus map;
• generating a refined depth map based, at least in part, on a combination of the generated initial depth map and the obtained at least one segmentation mask;
• and
• generating a blurred version of the first image based, at least in part, on the refined depth map.