Table 2 Recall values for different systems.

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

System type

Cond. scale

R@1 (%)

R@3 (%)

R@5 (%)

R@10 (%)

Random selection

–

0.85

2.50

4.20

8.50

Pure super-resolution

–

6.80

11.10

16.90

22.90

Super-resolution SLF

8

16.90

30.50

33.90

45.80

Super-resolution SLF (2)

4

13.60

20.30

27.10

35.60

Face generation SLF

2

9.30

16.10

23.70

34.70

Face generation SLF (2)

2

7.60

14.40

17.80

28.00

  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