Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

by   Kaixuan Wei, et al.

Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems. Although state-of-the-art methods can obtain decent results in certain situations, performance declines significantly when tackling more general real-world cases. These failures stem from the intrinsic difficulty of single image reflection removal -- the fundamental ill-posedness of the problem, and the insufficiency of densely-labeled training data needed for resolving this ambiguity within learning-based neural network pipelines. In this paper, we address these issues by exploiting targeted network enhancements and the novel use of misaligned data. For the former, we augment a baseline network architecture by embedding context encoding modules that are capable of leveraging high-level contextual clues to reduce indeterminacy within areas containing strong reflections. For the latter, we introduce an alignment-invariant loss function that facilitates exploiting misaligned real-world training data that is much easier to collect. Experimental results collectively show that our method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.


page 2

page 4

page 5

page 6

page 7

page 8


ReflectNet – A Generative Adversarial Method for Single Image Reflection Suppression

Taking pictures through glass windows almost always produces undesired r...

Iterative Gradient Encoding Network with Feature Co-Occurrence Loss for Single Image Reflection Removal

Removing undesired reflections from a photo taken in front of glass is o...

Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal

Removing reflection artefacts from a single-image is a problem of both t...

Clearing the Skies: A deep network architecture for single-image rain removal

We introduce a deep network architecture called DerainNet for removing r...

Learned Dual-View Reflection Removal

Traditional reflection removal algorithms either use a single image as i...

Single Image Reflection Removal through Cascaded Refinement

We address the problem of removing undesirable reflections from a single...

Benchmarking Ultra-High-Definition Image Reflection Removal

Deep learning based methods have achieved significant success in the tas...

Please sign up or login with your details

Forgot password? Click here to reset