Bi-Skip: A Motion Deblurring Network Using Self-paced Learning
This work addresses motion deblurring for applications in real-life imaging, but it appears incremental as it builds on existing GAN and self-paced learning techniques.
The paper tackles motion deblurring in images by combining self-paced learning with a GAN, using a Bi-Skip network and bi-level loss to improve generation and handle non-identical conditions, and demonstrates competitive advantage over state-of-the-art methods in evaluations.
A fast and effective motion deblurring method has great application values in real life. This work presents an innovative approach in which a self-paced learning is combined with GAN to deblur image. First, We explain that a proper generator can be used as deep priors and point out that the solution for pixel-based loss is not same with the one for perception-based loss. By using these ideas as starting points, a Bi-Skip network is proposed to improve the generating ability and a bi-level loss is adopted to solve the problem that common conditions are non-identical. Second, considering that the complex motion blur will perturb the network in the training process, a self-paced mechanism is adopted to enhance the robustness of the network. Through extensive evaluations on both qualitative and quantitative criteria, it is demonstrated that our approach has a competitive advantage over state-of-the-art methods.