Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks

The human visual system excels at detecting the local blur of visual images, but the underlying mechanism is not well understood. Traditional views of blur such as the reduction in energy at high frequencies and loss of phase coherence at localized features have fundamental limitations. For example, they cannot well discriminate flat regions from blurred ones. Here, we propose that the high-level semantic information is critical in successfully identifying the local blur. Therefore, we resort to deep neural networks that are proficient at learning high-level features and propose the first end-to-end local blur mapping algorithm based on a fully convolutional network. By analyzing various architectures with different depths and design philosophies, we empirically show that the high-level features of deeper layers play a more important role than the low-level features of shallower layers in resolving challenging ambiguities for this task. We test the proposed method on a standard blur detection benchmark and demonstrate that it significantly advances the state-of-the-art (ODS F-score of 0.853). Furthermore, we explore the use of the generated blur maps in three applications, including the blur region segmentation, blur degree estimation, and blur magnification.