single image haze removal using dark channel prior
DESCRIPTION
Single Image Haze Removal Using Dark Channel Prior Kaiming HeJian SunXiaoou Tangpresented by Djura SmitsChristiaan Meijer The Chinese University of Hong Kong Microsoft Research Asia. Estimating transmission. Abstract. Results. What is haze?. - PowerPoint PPT PresentationTRANSCRIPT
Single Image Haze Removal Using Dark Channel PriorKaiming He Jian Sun Xiaoou Tang presented by Djura Smits Christiaan MeijerThe Chinese University of Hong Kong Microsoft Research Asia
AbstractIn this paper, we propose a simple but effectiveimage prior - dark channel prior to remove haze from a singleinput image. The dark channel prior is a kind of statisticsof the haze-free outdoor images. It is based on a keyobservation - most local patches in haze-free outdoor imagescontain some pixels which have very low intensities inat least one color channel. Using this prior with the hazeimaging model, we can directly estimate the thickness of thehaze and recover a high quality haze-free image. Results ona variety of outdoor haze images demonstrate the power ofthe proposed prior. Moreover, a high quality depth map canalso be obtained as a by-product of haze removal.
Haze Removal
Dark channel prior
Dark channel prior
Estimating transmission
Soft matting
Results
Conclusions
Contact information
Djura SmitsStudent nr. [email protected]
Christiaan Meijer
In this paper, we have proposed a very simple but powerfulprior, called dark channel prior, for single image hazeremoval. The dark channel prior is based on the statistics ofthe outdoor images. Applying the prior into the haze imaging model, single image haze removal becomes simpler andmore effective.Since the dark channel prior is a kind of statistic, it maynot work for some particular images. When the scene objectsare inherently similar to the atmospheric light and noshadow is cast on them, the dark channel prior is invalid.Our method will underestimate the transmission for theseobjects, such as the white marble in Figure 13.Our work also shares the common limitation of mosthaze removal methods - the haze imaging model may be invalid.More advanced models [13] can be used to describecomplicated phenomena, such as the sun’s influence on thesky region, and the blueish hue near the horizon. We intendto investigate haze removal based on these models in thefuture.
Many images of outdoor scenes are degraded by the turbid medium (such as particles and water droplets) in the atmosphere. Haze, fog and smoke drastically reduce the visibility of objects further AWBZ of the camera. The goal of haze removal is to recover the radiance values of the objects in the image. There are different reasons why we would want to remove the haze from images. Firstly, the images may look more appealing, but more importantly, a lot of computer vision related processing is difficult on hazy images. Haze removal could be done as a preprocessing step to improve the performance of computer vision software.
Graphical representation of haze model
What is haze?
The model used to describe the formation of a haze image. The goal is to recover J, A and t from I.
Figure 3.The dark channel prior
Intuition: All patches in non-hazy images have an (almost) black value in one of the channels. Dehaze images by darkening patch so this statistic is restored.
Assuming transmission in a local patch is constant, transmission Can be computed in the following way
The refined transmission map t(x) is acquired by soft matting. The following cost function has to be minimized:
The optimal t can be obtained by solving the following sparse linear system:
In which L is defined as: