Disparity-based space-variant image deblurring

• We propose a disparity-based method of space-variant image deblurring.
• We employ disparity information in image segmentation, and estimate regional PSFs.
• The segmentation method firstly over-segments a blurred image based on color.
• Then, it merges adjacent regions with similar disparities.
• The experimental results show the effectiveness of the proposed method.

Obtaining a good-quality image requires exposure to light for an appropriate amount of time. If there is camera or object motion during the exposure time, the image is blurred. To remove the blur, some recent image deblurring methods effectively estimate a point spread function (PSF) by acquiring a noisy image additionally, and restore a clear latent image with the PSF. Since the groundtruth PSF varies with the location, a blockwise approach for PSF estimation has been proposed. However, the block to estimate a PSF is a straightly demarcated rectangle which is generally different from the shape of an actual region where the PSF can be properly assumed constant. We utilize the fact that a PSF is substantially related to the local disparity between two views. This paper presents a disparity-based method of space-variant image deblurring which employs disparity information in image segmentation, and estimates a PSF, and restores a latent image for each region. The segmentation method firstly over-segments a blurred image into sufficiently many regions based on color, and then merges adjacent regions with similar disparities. Experimental results show the effectiveness of the proposed method.

Graphical AbstractFigure optionsDownload as PowerPoint slide