Deep Idempotent Network for Efficient Single Image Blind Deblurring
This work addresses the trade-off between high performance and real-time processing in blind deblurring for image processing applications, offering a more efficient solution.
The paper tackles the problem of single image blind deblurring, which is ill-posed due to unknown sharp images and blur kernels, by introducing a deep idempotent network that achieves stable re-deblurring and is nearly 6.5X smaller and 6.4X faster than state-of-the-art methods while maintaining comparable performance.
Single image blind deblurring is highly ill-posed as neither the latent sharp image nor the blur kernel is known. Even though considerable progress has been made, several major difficulties remain for blind deblurring, including the trade-off between high-performance deblurring and real-time processing. Besides, we observe that current single image blind deblurring networks cannot further improve or stabilize the performance but significantly degrades the performance when re-deblurring is repeatedly applied. This implies the limitation of these networks in modeling an ideal deblurring process. In this work, we make two contributions to tackle the above difficulties: (1) We introduce the idempotent constraint into the deblurring framework and present a deep idempotent network to achieve improved blind non-uniform deblurring performance with stable re-deblurring. (2) We propose a simple yet efficient deblurring network with lightweight encoder-decoder units and a recurrent structure that can deblur images in a progressive residual fashion. Extensive experiments on synthetic and realistic datasets prove the superiority of our proposed framework. Remarkably, our proposed network is nearly 6.5X smaller and 6.4X faster than the state-of-the-art while achieving comparable high performance.