Simultaneous Inpainting and Colorization via Tensor Completion.

Both image inpainting and colorization can be considered as estimating certain missing pixel values from a given image, which is still a challenging problem in image processing. In fact, it is a more challenging problem to make image inpainting and colorization simultaneously, that is, given a corrupted gray-scale image and a few color pixels, we try to restore the original color image. In this paper, we propose a novel tensor completion model to solve the problem of simultaneous inpainting and colorization. Moreover, it can be applied to each of inpainting and colorization tasks separately as a special case. Experimental results on test images demonstrate that our proposed model is effective and efficient for simultaneous inpainting and colorization task and outperforms the state-of-the-art inpainting methods.