ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
This addresses a data scarcity problem in image deblurring for computer vision applications, offering a novel augmentation approach that is incremental in the broader field.
The paper tackles the lack of data augmentation for image deblurring by proposing ID-Blau, a method that generates diverse blurred images using implicit diffusion and blur condition maps, which significantly improves performance for state-of-the-art deblurring models.
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.