Abstract
We introduce an effective fusion-based technique to enhance both day-time and night-time hazy scenes. When inverting the Koschmieder light transmission model, and by contrast with the common implementation of the popular dark-channel DehazeHeCVPR2009, we estimate the airlight on image patches and not on the entire image. Local airlight estimation is adopted because, under night-time conditions, the lighting generally arises from multiple localized artificial sources, and is thus intrinsically non-uniform. Selecting the sizes of the patches is, however, non-trivial. Small patches are desirable to achieve fine spatial adaptation to the atmospheric light, but large patches help improve the airlight estimation accuracy by increasing the possibility of capturing pixels with airlight appearance (due to severe haze). For this reason, multiple patch sizes are considered to generate several images, that are then merged together. The discrete Laplacian of the original image is provided as an additional input to the fusion process to reduce the glowing effect and to emphasize the finest image details. Similarly, for day-time scenes we apply the same principle but use a larger patch size. For each input, a set of weight maps are derived so as to assign higher weights to regions of high contrast, high saliency and small saturation. Finally the derived inputs and the normalized weight maps are blended in a multi-scale fashion using a Laplacian pyramid decomposition. Extensive experimental results demonstrate the effectiveness of our approach as compared with recent techniques, both in terms of computational efficiency and the quality of the outputs.
Highlights
O UTDOOR images often suffer from poor visibility introduced by weather conditions, such as haze or fog
Our experiments have revealed that a smaller patch size is generally desired in night-time conditions, as compared to day time
We propose to adopt a multi-scale fusion approach to merge the images obtained with different patch-sizes, thereby allowing for effective and seamless enhancement of hazy night-time images
Summary
O UTDOOR images often suffer from poor visibility introduced by weather conditions, such as haze or fog. The technique presented here builds on our preliminary version, which was specific to night dehazing [20] In this extended version we generalize our solution to work effectively both on day and night-time hazy scenes. Small patches are desirable to achieve fine spatial adaptation, but small patches might lead to inaccurate airlight estimates due to the unavailability of pixels affected by strong haze when the patch becomes too small For this reason, we deploy multiple patch sizes, each generating a single input to a subsequent multi-scale fusion process. In addition to being effective in night-time conditions, our approach appears to naturally generalize to day-time scenes, by increasing the size of the patches in response to increased contrast and a wider distribution of color in the original image. It demonstrates the value of our approach as compared to recent techniques, both in terms of computational efficiency, and enhanced image quality
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call