Image Inpainting Based on Interactive Separation Network and Progressive Reconstruction Algorithm

doi:10.1109/ACCESS.2022.3186009

Image Inpainting Based on Interactive Separation Network and Progressive Reconstruction Algorithm

2022-01-01

3

OA

AI

张智强 (Zhang, Zhiqiang)

W

Wenxin Yu

DOI：10.1109/ACCESS.2022.3186009

Original

Original request for help

Save

Abstract

En 中文

Recently, learning-based image inpainting has gained much attention. It widely utilizes an auto-encoder structure and can obtain compact feature representation in the encoder to achieve high-quality image inpainting. Although this approach has achieved encouraging inpainting results, it inevitably reduces the high-resolution representation due to interval downsampling. In order to solve this problem and achieve an excellent image inpainting effect, this paper proposes a brand-new generative network, Interactive Separation Network, which retains the high-resolution information and extracts the semantic features from corrupted images. Furthermore, this paper also discusses network designs with different complexity in different application scenarios. Finally, to improve the effectiveness and robustness of our proposal to large corrupted regions in the inpainting image, we further propose a flexible and highly reusable reconstruction scheme to complete the inpainting in the prediction process gradually. Experiments show that our proposed generation network and reconstruction scheme can significantly improve the quality of repaired images. The proposed method significantly outperforms the state-of-the-art image inpainting approaches in image quality.

Keywords:

Semantics

Image reconstruction

Feature extraction

Generative adversarial networks

Image edge detection

Task analysis

Robustness

Image inpainting

image completion

feature fusion

reconstruction algorithms

Image Inpainting Based on Interactive Separation Network and Progressive Reconstruction Algorithm

Abstract

Journal

Organization