Iterative Gradient Encoding Network with Feature Co-Occurrence Loss for Single Image Reflection Removal
This addresses the challenge of generalizing reflection removal across diverse reflection types for visual computing systems, representing an incremental improvement over prior methods.
The paper tackles the problem of removing reflections from single images taken through glass, proposing an iterative gradient encoding network with a feature co-occurrence loss that outperforms state-of-the-art methods on the SIR^2 benchmark, especially as reflection strength increases.
Removing undesired reflections from a photo taken in front of glass is of great importance for enhancing visual computing systems' efficiency. Previous learning-based approaches have produced visually plausible results for some reflections type, however, failed to generalize against other reflection types. There is a dearth of literature for efficient methods concerning single image reflection removal, which can generalize well in large-scale reflection types. In this study, we proposed an iterative gradient encoding network for single image reflection removal. Next, to further supervise the network in learning the correlation between the transmission layer features, we proposed a feature co-occurrence loss. Extensive experiments on the public benchmark dataset of SIR$^2$ demonstrated that our method can remove reflection favorably against the existing state-of-the-art method on all imaging settings, including diverse backgrounds. Moreover, as the reflection strength increases, our method can still remove reflection even where other state of the art methods failed.