Removing Non-Uniform Motion Blur from Images

We propose a method for removing non-uniform motion blur from multiple blurry images. Traditional methods focus on estimating a single motion blur kernel for the entire image. In contrast, we aim to restore images blurred by unknown, spatially varying motion blur kernels caused by different relative motions between the camera and the scene. Our algorithm simultaneously estimates multiple motions, motion blur kernels, and the associated image segments. We formulate the problem as a regularized energy function and solve it using an alternating optimization technique. Realworld experiments demonstrate the effectiveness of the proposed method.

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Sunghyun Cho, Yasuyuki Matsushita, Seungyong Lee
• Keywords: Computer Vision, ICCV 2007, Motion Blur Kernels, Multiple Blurry Images, Multiple Motions, Non-uniform Motion Blur