Table 3 Gender, ethnicity and age group recalls, as well as, the root mean square errors of age for different systems.

From: Scalable multimodal approach for face generation and super-resolution using a conditional diffusion model

System type

Cond. Scale

Gender recall (%)

Ethnicity recall (%)

Age group recall (%)

RMSE of Age (years)

Pure super-resolution

-

78.80

37.30

44.10

7.54

Super-resolution SLF

8

90.70

65.30

57.60

5.62

Super-resolution SLF (2)

4

85.60

53.40

52.50

5.77

Face generation SLF

2

88.10

58.50

72.90

5.11

Face generation SLF (2)

2

87.30

51.70

49.20

6.99

  1. The second entry for the face super-resolution and the face generation SLF systems are calculated without specifying values for the additional attributes, since they are optional inputs.
  2. Significant values are given in bold.
Back to article page