Abstract
We present a highly efficient blind restoration method to remove mild blur in natural images. Contrary to the mainstream, we focus on removing slight blur that is often present, damaging image quality and commonly generated by small out-of-focus, lens blur, or slight camera motion. The proposed algorithm first estimates image blur and then compensates for it by combining multiple applications of the estimated blur in a principled way. To estimate blur we introduce a simple yet robust algorithm based on empirical observations about the distribution of the gradient in sharp natural images. Our experiments show that, in the context of mild blur, the proposed method outperforms traditional and modern blind deblurring methods and runs in a fraction of the time. Our method can be used to blindly correct blur before applying off-the-shelf deep super-resolution methods leading to superior results than other highly complex and computationally demanding techniques. The proposed method estimates and removes mild blur from a 12MP image on a modern mobile phone in a fraction of a second.
Highlights
I MAGE sharpness is undoubtedly one of the most relevant attributes defining the visual quality of a photograph
Removing blur from images is a longstanding problem in image processing and computational photography spanning more than 50 years [1]–[3]
We introduced a highly efficient algorithm for estimating and removing mild blur that is ubiquitously present in many captured images
Summary
I MAGE sharpness is undoubtedly one of the most relevant attributes defining the visual quality of a photograph. The gain in quality is in many cases extraordinary, but impractical These methods make extensive use of prior information (learned or modeled) producing images that are often unrealistic. We present a mathematical characterization of halos and propose a blending mechanism to render an artifact-free final image This step, which is highly efficient, is important to achieve consistent high quality. Experiments with both real and synthetic data show that, in the context of mild blur in natural images, our proposed method outperforms traditional and modern blind deblurring methods and runs in a fraction of the time. We introduce a novel method to estimate and remove mild blur (very common in mobile photography) that is (i) highly efficient and simple, (ii) theoretically sound, and (iii) produces competitive or better results while being orders of magnitude faster.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
