Image restoration

Combinatorics

Image (mathematics)

Electrical engineering

Machine learning

Engineering

Fuse (electrical)

Paleontology

Leverage (statistics)

Pattern recognition (psychology)

Artificial intelligence

Psychology

Economics

Set (abstract data type)

Management

Programming language

Code (set theory)

Context (archaeology)

Task (project management)

Dilation (metric space)

Generality

Computer vision

Mathematics

Computer science

Convolution (computer science)

Artificial neural network

Psychotherapist

Margin (machine learning)

Biology

Image processing

Image dehazing aims to recover the uncorrupted content from a hazy image. Instead of leveraging traditional low-level or handcrafted image priors as the restoration constraints, e.g., dark channels and increased contrast, we propose an end-to-end gated context aggregation network to directly restore the final haze-free image. In this network, we adopt the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters, and leverage a gated sub-network to fuse the features from different levels. Extensive experiments demonstrate that our method can surpass previous state-of-the-art methods by a large margin both quantitatively and qualitatively. In addition, to demonstrate the generality of the proposed method, we further apply it to the image deraining task, which also achieves the state-of-the-art performance. Code has been made available at https://github.com/cddlyf/GCANet.

Gated Context Aggregation Network for Image Dehazing and Deraining