Paper
1 May 2022 Image inpainting based on directional Gaussian graph model using multi-head reference
Zhonghao Zhang, Lihong Ma
Author Affiliations +
Proceedings Volume 12171, Thirteenth International Conference on Signal Processing Systems (ICSPS 2021); 1217113 (2022) https://doi.org/10.1117/12.2631560
Event: Thirteenth International Conference on Signal Processing Systems (ICSPS 2021), 2021, Shanghai, China
Abstract
This paper aims to repair missing regions which are corrupted along arbitrary directions. It presents a mixed image inpainting method based on Markov random field. By using Belief Propagation scheme in low gray-levels and alternately suggesting a directional Gaussian Graphical model (DGGM) for multiple references in a high-level range, it gains a balance between the model accuracy and the computation complexity in realization. On the basis of an existing method in [1], it improves the method in high level inpainting for the task under small train sets and large corrupted regions, by introducing these multi-head reference clues. Experimental results are given, the inpainting quality of different kinds of images with different sizes and contents under different parameter settings are compared in metrics of the peak signal noise ratio and the structural similarity index. The significance of parameter settings and the efficient computational cost could demonstrate the feasibility of this method.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhonghao Zhang and Lihong Ma "Image inpainting based on directional Gaussian graph model using multi-head reference", Proc. SPIE 12171, Thirteenth International Conference on Signal Processing Systems (ICSPS 2021), 1217113 (1 May 2022); https://doi.org/10.1117/12.2631560
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image quality

Contamination

Image restoration

Head

Magnetorheological finishing

Image resolution

Diffusion

Back to Top