IMAGE HAZE REMOVAL USING FAST CONSTRAINED TRANSMISSION ESTIMATION

摘要

Techniques are disclosed for removing haze from an image or video by constraining the medium transmission used in a haze image formation model. In particular, a de-hazed scene, which is a function of a medium transmission, is constrained to be greater than or equal to a fractionally scaled variant of the input image. The degree to which the input image is scaled can be selected manually or by using machine learning techniques on a pixel-by-pixel basis to achieve visually pleasing results. Next, the constrained medium transmission is filtered to be locally smooth with sharp discontinuities along image edge boundaries to preserve scene depth. This filtering results in a prior probability distribution that can be used for haze removal in an image or video frame. The input image is converted to gamma decoded sRGB linear space prior to haze removal, and gamma encoded into sRGB space after haze removal.

主权项

1. A computer-implemented digital image processing method comprising:
receiving, by a processor, input data representing an input digital image having a plurality of pixels; modeling a scene radiance vector of the input image as a function of the input digital image, an atmospheric light factor, and a medium transmission for each of the pixels in the input digital image; calculating, by the processor, the medium transmission for each of the pixels in the input digital image based on a fractionally scaled variant of the corresponding pixel in the input digital image; filtering, by the processor, the medium transmissions using a smoothing function, such that a given neighborhood of pixels corresponding to one of the medium transmissions is locally smooth; and recovering, by the processor, the scene radiance vector based at least in part on the filtered medium transmission for each pixel in the input digital image, the recovered scene radiance vector representing a de-hazed digital image in which at least some haze effects in the input digital image are removed.