Separating Reflection and Transmission Images in the Wild
The reflections caused by common semi-reflectors, such as glass windows, can severely impact the performance of computer vision algorithms. State-of-the-art works can successfully remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and fail to generalize to real-world images---even when they leverage polarization. We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance. Key to our approach is our synthetic data generation, which accurately simulates reflections, including those generated by curved and non-ideal surfaces, and non-static scenes. We extensively validate our method against a number of related works on a new dataset of images captured in the wild.
READ FULL TEXT