Hu, J., Wang, C., Zhang, Y., Liu, L., Yin, Y., & Zimmermann, R. (2022). Parallel Edge-Image Learning for Image Inpainting. 2022 IEEE International Conference on Multimedia and Expo (ICME). https://doi.org/10.1109/icme52920.2022.9859715
Abstract:
The primary goal of image inpainting is to fix holes in a damaged image with natural contents. A key challenge is that a damaged image contains complex structures in different ways, with each consisting of its configuration of edges and spatial dependencies. As a result, filled images often converge to unnatural and implausible results. Currently, the edge-image inpainting methods adopt two stages to recover edges and images successively, which suffer from feature inconsistency and error accumulation. This leads us to present a parallel edge-image learning framework that explicitly characterizes these internal configurations in a single stage. The framework introduces a dual parallel network-based decoder to generate the image and the edges concurrently, leading to feature consistency at the semantic level. Also, a new crossfire mechanism aims to exchange edge-image information in the decoder, avoiding error accumulation. Empirical evaluations on benchmark datasets suggest that our approach outperforms the state-of-the-art methods on image inpainting.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Ministry of Education - Academic Research Fund Tier 1
Grant Reference no. : T1 251RES2029
National Major Science and Technology Projects of China (grant no.
2018AAA0100703), the National Natural Science Foundation of China (grant nos. 61977012)