Table 7 PSNR 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

PSNR (dB)

Minimum

Maximum

Average

MSDN

49.25

63.87

56.56

FLTNet

52.69

64.46

58.58

MGNet

51.71

62.11

56.91

AOT Method

61.02

64.79

62.91

EC Model

58.76

64.15

61.46

LaMa Method

58.76

64.15

61.46

LID-MIR

58.71

63.55

61.13

HDLIP-SHAR

61.42

67.76

64.59

Back to article page