Perception-Aware Contrastive Learning-Based Progressive Image Inpainting

Keyu Liu, Shibo Li, Yajun Qiu, Feiyu Chen, Shuyuan Zhu, Bing Zeng, Fan Zhang

Abstract: Deep-learning-based image inpainting has demonstrated impressive performance in improving the visual quality of the inpainted content. However, existing methods still generate unpleasant content, especially in cases with large broken areas. To solve this problem, we propose a perception-aware contrastive learning-based progressive image inpainting approach, which is implemented in an iterative way to refine the details of the inpainted images. To produce results with improved visual quality, a contrastive learning strategy coupled with a perceptual loss is adopted in the refinement process for model optimization. The experimental results demonstrate excellent performance of the proposed method as proved by up to a 5.48% gain on the Frechet inception distance and 1.87% gain on the learned perceptual image patch similarity, compared with the state-of-the-art approach.

External IDs:dblp:journals/ieeemm/LiuLQCZZZ25