ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation

TL;DR

ID-Blau introduces a novel data augmentation method for image deblurring that uses implicit diffusion to generate diverse realistic blurred images, enhancing the training of deblurring models.

Contribution

The paper presents a new blur augmentation technique based on implicit diffusion, enabling the creation of diverse blurred images by simulating motion trajectories in a continuous space.

Findings

ID-Blau generates realistic blurred images for training.

Using ID-Blau improves deblurring model performance.

The method effectively simulates diverse motion blurs.

Abstract

Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data augmentation for image deblurring. Since continuous motion causes blurred artifacts during image exposure, we aspire to develop a groundbreaking blur augmentation method to generate diverse blurred images by simulating motion trajectories in a continuous space. This paper proposes Implicit Diffusion-based reBLurring AUgmentation (ID-Blau), utilizing a sharp image paired with a controllable blur condition map to produce a corresponding blurred image. We parameterize the blur patterns of a blurred image with their orientations and magnitudes as a pixel-wise blur condition map to simulate motion trajectories and implicitly represent them in a continuous space. By sampling diverse blur conditions, ID-Blau can generate various blurred images unseen in the training set. Experimental results demonstrate that ID-Blau can produce realistic blurred images for training and thus significantly improve performance for state-of-the-art deblurring models. The source code is available at https://github.com/plusgood-steven/ID-Blau.