Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization

arXiv:2404.12168v1 Announce Type: new
Abstract: As recent advances in mobile camera technology have enabled the capability to capture high-resolution images, such as 4K images, the demand for an efficient deblurring model handling large motion has increased. In this paper, we discover that the image residual errors, i.e., blur-sharp pixel differences, can be grouped into some categories according to their motion blur type and how complex their neighboring pixels are. Inspired by this, we decompose the deblurring (regression) task into blur …

abstract advances arxiv blind camera technology capability cs.ai cs.cv demand differences errors image images mobile paper pixel residual resolution technology type via world