Blind Deconvolution for Color Images Using Normalized Quaternion Kernels
By: Yuming Yang , Michael K. Ng , Zhigang Jia and more
Potential Business Impact:
Cleans up blurry color pictures by understanding colors.
In this work, we address the challenging problem of blind deconvolution for color images. Existing methods often convert color images to grayscale or process each color channel separately, which overlooking the relationships between color channels. To handle this issue, we formulate a novel quaternion fidelity term designed specifically for color image blind deconvolution. This fidelity term leverages the properties of quaternion convolution kernel, which consists of four kernels: one that functions similarly to a non-negative convolution kernel to capture the overall blur, and three additional convolution kernels without constraints corresponding to red, green and blue channels respectively model their unknown interdependencies. In order to preserve image intensity, we propose to use the normalized quaternion kernel in the blind deconvolution process. Extensive experiments on real datasets of blurred color images show that the proposed method effectively removes artifacts and significantly improves deblurring effect, demonstrating its potential as a powerful tool for color image deconvolution.
Similar Papers
A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation
CV and Pattern Recognition
Makes pictures look more real by fixing colors.
DeepRFTv2: Kernel-level Learning for Image Deblurring
CV and Pattern Recognition
Cleans blurry pictures by learning how they got blurry.
Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
CV and Pattern Recognition
Helps computers see objects from any angle.