Explore Image Deblurring via Blur Kernel Space
This addresses the problem of handling diverse and unseen blur types in image deblurring for computer vision applications, offering a novel approach that is differentiable and adaptable.
The paper tackles blind image deblurring by encoding blur operators into a kernel space and using an alternating optimization algorithm to handle unseen blur kernels, avoiding complex handcrafted priors and enabling blur synthesis across domains.
This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space. Assuming the encoded kernel space is close enough to in-the-wild blur operators, we propose an alternating optimization algorithm for blind image deblurring. It approximates an unseen blur operator by a kernel in the encoded space and searches for the corresponding sharp image. Unlike recent deep-learning-based methods, our system can handle unseen blur kernel, while avoiding using complicated handcrafted priors on the blur operator often found in classical methods. Due to the method's design, the encoded kernel space is fully differentiable, thus can be easily adopted in deep neural network models. Moreover, our method can be used for blur synthesis by transferring existing blur operators from a given dataset into a new domain. Finally, we provide experimental results to confirm the effectiveness of the proposed method.