Separating Reflection and Transmission Images in the Wild
This addresses the issue of reflection removal for computer vision algorithms in uncontrolled environments, representing a domain-specific advancement.
The paper tackles the problem of separating reflection and transmission images in real-world scenarios, where existing methods fail due to strong assumptions, by presenting a deep learning approach that uses polarization properties and achieves results on realistic synthetic data.
The reflections caused by common semi-reflectors, such as glass windows, can impact the performance of computer vision algorithms. State-of-the-art methods can remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and do not generalize well to real-world images. Contrary to a common misconception, real-world images are challenging even when polarization information is used. We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance, which explicitly uses the polarization properties of light. To train it, we introduce an accurate synthetic data generation pipeline, which simulates realistic reflections, including those generated by curved and non-ideal surfaces, non-static scenes, and high-dynamic-range scenes.