Can fully convolutional networks perform well for general image restoration problems?
This addresses the problem of improving image restoration quality for applications like photography and medical imaging, but it is incremental as it adapts existing FCN architectures to low-level vision tasks.
The paper investigated whether fully convolutional networks (FCNs) can effectively perform image restoration tasks, such as denoising and blind inpainting, by learning an end-to-end mapping from corrupted to clean images. The results showed that the FCN model outperformed traditional sparse coding methods and achieved competitive performance compared to state-of-the-art methods for denoising, with impressive visual quality in inpainting.
We present a fully convolutional network(FCN) based approach for color image restoration. FCNs have recently shown remarkable performance for high-level vision problem like semantic segmentation. In this paper, we investigate if FCN models can show promising performance for low-level problems like image restoration as well. We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output. Our proposed method takes inspiration from domain transformation techniques but presents a data-driven task specific approach where filters for novel basis projection, task dependent coefficient alterations, and image reconstruction are represented as convolutional networks. Experimental results show that our FCN model outperforms traditional sparse coding based methods and demonstrates competitive performance compared to the state-of-the-art methods for image denoising. We further show that our proposed model can solve the difficult problem of blind image inpainting and can produce reconstructed images of impressive visual quality.