Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images
This addresses the dataset bottleneck for researchers and practitioners in image deblurring, though it is incremental as it builds on existing methods.
The paper tackled the problem of training deep networks for motion deblurring that generalize poorly to real images due to limited datasets, by proposing a procedural method to generate realistic sharp/blurred pairs, which improved generalization performance in cross-dataset evaluations on real blurred images.
Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains a challenging task. In this paper, we first review the limitations of existing deblurring benchmark datasets and analyze the underlying causes for deblurring networks' lack of generalization to blurry images in the wild. Based on this analysis, we propose an efficient procedural methodology to generate sharp/blurred image pairs based on a simple yet effective model. This allows for generating virtually unlimited diverse training pairs mimicking realistic blur properties. We demonstrate the effectiveness of the proposed dataset by training existing deblurring architectures on the simulated pairs and performing cross-dataset evaluation on three standard datasets of real blurred images. When training with the proposed method, we observed superior generalization performance for the ultimate task of deblurring real motion-blurred photos of dynamic scenes.