Table 8 SSIM outcome of HDLIP-SHAR approach with existing models.

From: Automated image inpainting for historical artifact restoration using hybridisation of transfer learning with deep generative models

Methods

SSIM

Minimum

Maximum

Average

MSDN

0.801

0.985

0.893

FLTNet

0.806

0.979

0.893

MGNet

0.853

0.970

0.912

AOT Method

0.850

0.978

0.914

EC Model

0.866

0.977

0.922

LaMa Method

0.861

0.980

0.921

LID-MIR

0.866

0.988

0.927

HDLIP-SHAR

0.899

0.991

0.945

Back to article page