No abstract

No abstract

Reflection in an image is not always desirable due to the loss of information. Conventional methods to remove reflection are based on priors that require certain conditions to be fulfilled. Recent advancements of deep learning in many fields have revolutionized these traditional approaches. Using input images more than one reduces the ill-posedness of the problem statement.Standard assumption in numerous methods assumes background is stationary and only reflection layer is varying. However, images at different angles have slightly different backgrounds. Considering this a new dataset is created where both reflection and background layer is varying. In this paper, a two-image based method with an end to end mapping between the observed images and background is presented. The key feature is the practicability of the method, wherein a sequence of images at slightly different angles can easily be captured using modern dual camera mobile devices. A combination of feature loss with MSE maintains the content and quality of the resultant image.

Due to the presence of an additional glass pane between the camera and the scene, an additional reflection scene is captured in the image apart from the desired object sometimes. Images are more often captured from mobile handsets these days which have multiple cameras. This paper gives the advantage of multiple cameras. There exists a disparity and varied field of view when images are captured with multiple cameras. We use these two factors to act as a cue to remove reflection, as reflection intensity across the image pairs change with different field-of-view. The proposed method is robust and convenient to implement as it does not require an additional hardware, for example, light field camera for stereo images. Also, it does not make assumptions about the appearance or intensity of reflection.