Learning to See through Reflections

Jin, Meiguang; Süsstrunk, Sabine; Favaro, Paolo (May 2018). Learning to See through Reflections. In: IEEE International Conference on Computational Photography 2018. Pittsburgh, PA, United States. May 4 - May 6, 2018. 10.1109/ICCPHOT.2018.8368464

Text 08368464.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (2MB)

Pictures of objects behind a glass are difficult to interpret and understand due to the superposition of two real images: a reflection layer and a background layer. Separation of these two layers is challenging due to the ambiguities in assigning texture patterns and the average color in the input image to one of the two layers. In this paper, we propose a novel method to reconstruct these layers given a single input image by explicitly handling the ambiguities of the reconstruction. Our approach combines the ability of neural networks to build image priors on large image regions with an image model that accounts for the brightness ambiguity and saturation. We find that our solution generalizes to real images even in the presence of strong reflections. Extensive quantitative and qualitative experimental evaluations on both real and synthetic data show the benefits of our approach over prior work. Moreover, our proposed neural network is computationally and memory efficient.

Interest & Impact

Downloads

3 since deposited on 29 May 2019
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item