Combining multiple images in bracketed photography

摘要

Embodiments provide a unified method for combining images such as high dynamic range images, flash-no-flash image pairs, and/or other images. Weight masks are defined for each of the plurality of images by calculating coefficients for each of the weight masks. Calculating the coefficients includes, at least, performing histogram alignment between a reference image and each of the other input images and by applying a mismatch bias to the coefficients as a function of the histogram alignment. After applying the weight masks to the corresponding images, the images are combined to produce a final image.

主权项

1. A method comprising:
accessing a plurality of images, wherein one of the plurality of images is a reference image; defining weight masks each corresponding to one of the accessed plurality of images, said defining including calculating coefficients for each of the weight masks by:
performing histogram alignment between the reference image and each other image in the plurality of images, andapplying mismatch bias to the coefficients as a function of the performed histogram alignment; applying the defined weight masks to the corresponding images; and blending the plurality of images having the applied weight masks to produce a final image.