Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
This addresses the demand for efficient deblurring in mobile photography, offering a practical solution for handling 4K images, though it is incremental as it builds on existing deblurring methods.
The paper tackles the problem of efficiently deblurring high-resolution images with large motion blur by decomposing the regression task into blur pixel discretization and conversion steps, achieving comparable performance to state-of-the-art methods while being up to 10 times more computationally efficient.
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 pixel discretization (pixel-level blur classification) and discrete-to-continuous conversion (regression with blur class map) tasks. Specifically, we generate the discretized image residual errors by identifying the blur pixels and then transform them to a continuous form, which is computationally more efficient than naively solving the original regression problem with continuous values. Here, we found that the discretization result, i.e., blur segmentation map, remarkably exhibits visual similarity with the image residual errors. As a result, our efficient model shows comparable performance to state-of-the-art methods in realistic benchmarks, while our method is up to 10 times computationally more efficient.