ECP

Image deblurring via extreme channels prior

Yanyang Yan, Wenqi Ren, Yuanfang Guo, Rui Wang, Xiaochun Cao

Abstract

Camera motion introduces motion blur, affecting many computer vision tasks. Dark Channel Prior (DCP) helps the blind deblurring on scenes including natural, face, text, and low-illumination images. However, it has limitations and is less likely to support the kernel estimation while bright pixels dominate the input image. We observe that the bright pixels in the clear images are not likely to be bright after the blur process. Based on this observation, we first illustrate this phenomenon mathmatically and define it as the Bright Channel Prior (BCP). Then, we propose a technique for deblurring such images which elevates the performance of existing motion deblurring algorithms. The proposed method takes advatage of both Bright and Dark Prior. This joint prior is named as extreme channels prior and is crucial for achieving efficient restorations by leveraging both the bright and dark information. Extensive experimental results demostrate that the proposed method is more robust and performs favorably against the state-of-the-art image deblurring methods on both synthesized and natural images.

The intensities of bright channel pixels decrease after the blurring process. Maximizing the bright channel helps image recovering.