Reference-guided face inpainting with reference attention network

Yu, Jiazuo; Li, Kai; Peng, Jinjia

doi:10.1007/s00521-022-06961-8

Cited by 7 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the depth inpainting model, the disadvantages of the single-stage model [ 34 , 35 , 36 , 37 , 38 , 39 ], such as the lack of texture details of the generated image, the fuzzy structural problem still cannot be effectively solved. Most coarse-to-fine models [ 40 , 41 , 42 , 43 , 44 , 45 , 46 ] can produce more realistic textures, so many researchers are committed to improving the coarse-to-fine image inpainting model. However, they lack details in the rough repair stage.…”

Section: Related Workmentioning

confidence: 99%

Multi-Step Structure Image Inpainting Model with Attention Mechanism

Cai

Yang

2023

Sensors

View full text Add to dashboard Cite

The proliferation of deep learning has propelled image inpainting to an important research field. Although the current image inpainting model has made remarkable achievements, the two-stage image inpainting method is easy to produce structural errors in the rough stage because of insufficient treatment of the rough inpainting stage. To address this problem, we propose a multi-step structured image inpainting model combining attention mechanisms. Different from the previous two-stage inpainting model, we divide the damaged area into four sub-areas, calculate the priority of each area according to the priority, specify the inpainting order, and complete the rough inpainting stage several times. The stability of the model is enhanced by the multi-step method. The structural attention mechanism strengthens the expression of structural features and improves the quality of structure and contour reconstruction. Experimental evaluation of benchmark data sets shows that our method effectively reduces structural errors and improves the effect of image inpainting.

show abstract