Photo-realistic shallow depth-of-field rendering from focal stacks

Abstract

The invention relates to photo-realistic shallow depth-of-field rendering from focal stacks. Generating an image with a selected level of background blur includes capturing, by a first image capture device, a plurality of frames of a scene, wherein each of the plurality of frames has a different focus depth, obtaining a depth map of the scene, determining a target object and a background in the scene based on the depth map, determining a goal blur for the background, and selecting, for each pixel in an output image, a corresponding pixel from the focus stack.

Description

Background technique [0001] This disclosure relates generally to the field of digital image capture and processing, and more particularly to the field of rendering realistic shallow depth of field through focus stacks. The camera can adjust the lens stack to focus on the subject. A camera's autofocus (AF) system can, for example, automatically adjust the lens stack to focus on an object. A particular image may require several objects to be in focus. [0002] Focus stacks provide multiple focus settings for a set of images, making multiple objects in an image appear sharp in different images. Focus stacking combines multiple images with different focal points to form a final image that is overall sharper than the individual images. To ensure that all points in the scene are captured clearly, the lens stack needs to be turned from large lens to infinity mode. For example, a camera may capture a series of images at a predetermined depth with a lens stack. At each depth, a di...

AI Technical Summary

Problems solved by technology

However, the more images captured, the more processing power is required,

Images