Find in Library

Most existing image deblurring methods are based on the estimation of blur kernels and end-to-end learning of the mapping relationship between blurred and sharp images. However, since different real-world blurred images typically have completely different blurring patterns, the performance of these methods in real image deblurring tasks is limited without explicitly modeling blurring as degradation representations. In this paper, we propose <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>IDR</mi><mn>2</mn></msup><mi>ENet</mi></mrow></semantics></math></inline-formula>, which is the Implicit Degradation Representations and Reblur Estimation Network, for real image deblurring. <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>IDR</mi><mn>2</mn></msup><mi>ENet</mi></mrow></semantics></math></inline-formula> consists of a degradation estimation process, a reblurring process, and a deblurring process. The degradation estimation process takes the real blurred image as input and outputs the implicit degradation representations estimated on it, which are used as the inputs of both reblurring and deblurring processes to better estimate the features of the blurred image. The experimental results show that whether compared with traditional or deep-learning-based deblurring algorithms, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>IDR</mi><mn>2</mn></msup><mi>ENet</mi></mrow></semantics></math></inline-formula> achieves stable and efficient deblurring results on real blurred images.