Grave Artifacts in Image Inpainting: Investigating the Causes and Untangling the Factors

Rodrigues, Walber M.; Walmsley, Felipe N.; Cavalcanti, George D. C.; Quintino, Jonysberg P.; Pinho, Helder

doi:10.1109/access.2021.3108015

Search citation statements

Order By: Relevance

Paper Sections

Select...

Metrics1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Other3

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where PMAX represents the maximum possible pixel value of the image, and MSE [14] represents the mean square error, which measures the average squared difference between the restored image and the original image.…”

Section: Metricsmentioning

confidence: 99%

An image inpainting method based on the high-efficiency transformer

Yang,

2024

International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024)

View full text Add to dashboard Cite

In this paper, we introduce an image restoration network that is based on the High-Efficiency Transformer (HET). The model utilizes fast Fourier convolution for image enhancement, incorporates self-attention mechanisms for capturing contextual information, and employs convolution for feature extraction and classification. Additionally, we improve the network's performance and convergence speed by implementing batch normalization and residual concatenation. Experimental results show substantial enhancements in image restoration achieved through our deep learning-based approach. The reconstructed images demonstrate improved clarity, enhanced details, and reduced dependence on manual interventions.

show abstract

Section: Metricsmentioning

confidence: 99%