Visibility

Abstract: Images captured under low-light conditions often suffer from (partially) poor visibility. Besides unsatisfactory lightings, multiple types of degradations, such as noise and color distortion due to the limited quality of cameras, hide in the dark. In other words, solely turning up the brightness of dark regions will inevitably amplify hidden artifacts. This work builds a simple yet effective network for Kindling the Darkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components. One component (illumination) is responsible for light adjustment, while the other (reflectance) for degradation removal. In such a way, the original space is decoupled into two smaller subspaces, expecting to be better regularized/learned. It is worth to note that our network is trained with paired images shot under different exposure conditions, instead of using any ground-truth reflectance and illumination information. Extensive experiments are conducted to demonstrate the efficacy of our design and its superiority over state-of-the-art alternatives. Our KinD is robust against severe visual defects, and user-friendly to arbitrarily adjust light levels. In addition, our model spends less than 50ms to process an image in VGA resolution on a 2080Ti GPU. All the above merits make our KinD attractive for practical use.

Abstract: 12 There is currently a misconception among designers and users of free space laser communication (lasercom) equipment that 1550 nm light suffers from less atmospheric attenuation than 785 or 850 nm light in all weather conditions. This misconception is based upon a published equation for atmospheric attenuation as a function of wavelength, which is used frequently in the free-space lasercom literature. In hazy weather (visibility > 2 km), the prediction of less atmospheric attenuation at 1550 nm is most likely true. However, in foggy weather (visibility < 500 m), it appears that the attenuation of laser light is independent of wavelength, ie. 785 nm, 850 nm, and 1550 nm are all attenuated equally by fog. This same wavelength independence is also observed in snow and rain. This observation is based on an extensive literature search, and from full Mie scattering calculations. A modification to the published equation describing the atmospheric attenuation of laser power, which more accurately describes the effects of fog, is offered. This observation of wavelength-independent attenuation in fog is important, because fog, heavy snow, and extreme rain are the only types of weather that are likely to disrupt short (< 500 m) lasercom links. Short lasercom links will be necessary to meet the high availability requirements of the telecommunications industry.

Abstract: Images of outdoor scenes captured in bad weather suffer from poor contrast. Under bad weather conditions, the light reaching a camera is severely scattered by the atmosphere. The resulting decay in contrast varies across the scene and is exponential in the depths of scene points. Therefore, traditional space invariant image processing techniques are not sufficient to remove weather effects from images. We present a physics-based model that describes the appearances of scenes in uniform bad weather conditions. Changes in intensities of scene points under different weather conditions provide simple constraints to detect depth discontinuities in the scene and also to compute scene structure. Then, a fast algorithm to restore scene contrast is presented. In contrast to previous techniques, our weather removal algorithm does not require any a priori scene structure, distributions of scene reflectances, or detailed knowledge about the particular weather condition. All the methods described in this paper are effective under a wide range of weather conditions including haze, mist, fog, and conditions arising due to other aerosols. Further, our methods can be applied to gray scale, RGB color, multispectral and even IR images. We also extend our techniques to restore contrast of scenes with moving objects, captured using a video camera.