Abstract
An image captured through a glass plane usually contains both of a target transmitted scene behind the glass plane and a reflected scene in front of the glass plane. We propose a semantic context based network to remove reflection artifacts from a single glass image. We first investigate a non-linear intensity mapping relationship for glass images to synthesize more realistic training sets. Then we devise an efficient reflection removal network using multi-scale generators and an interpreter, where the semantic context of the transmission image is adopted as a high level cue for the interpreter to guide the generators. We also provide a new test data set of real glass images including the ground truth transmission and reflection images. Experiments are performed on four test data sets and we show that the proposed algorithm decomposes an input glass image into a transmission image and a reflection image more faithfully compared with the four existing state-of-the-art methods.
Highlights
Glass material has been used in many places, for example, glass display windows in retail shops are used to show products to customers while protecting the products
We provide a new data set of real glass images including 71 triplets of glass image, transmission image and reflection image
A glass image is taken by placing a glass plane in front of camera, and the associated ground truth reflection image is captured by attaching a black opaque sheet behind the glass plane
Summary
Glass material has been used in many places, for example, glass display windows in retail shops are used to show products to customers while protecting the products. Lots of attempts have been made to reconstruct transmission images faithfully by removing reflection artifacts from glass images. Many existing methods use multiple glass images taken under different capturing conditions to extract the characteristics of typical reflection images. Special capturing environments are often required such as replacing camera filters or adjusting focal lengths, which cause limitations to practical application. Single image based reflection removal techniques employ unique characteristics of reflection images such as smoothness prior [4] or ghosting cue [5], The associate editor coordinating the review of this manuscript and approving it for publication was Shuping He
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
