Table 4 Ablation study of parameter \(\alpha\) in the loss function.

From: Cross-range self-attention single hyperspectral image super-resolution method based on U-Net architecture

\(\alpha\)

d

HR_image_size

\(\text {PSNR}\uparrow\)

\(\text {SSIM}\uparrow\)

\(\text {SAM}\downarrow\)

\(\text {ERGAS}\downarrow\)

\(\text {CC}\uparrow\)

0.1

4

64 × 64

39.7432

0.9053

9.7285

6.2728

0.8725

0.01

4

64 × 64

39.7431

0.9046

9.7258

6.3828

0.8718

0.001

4

64 × 64

39.7734

0.9047

9.6871

6.2503

0.8739

0.0001

4

64 × 64

39.6636

0.9036

9.9310

6.3742

0.8679

0.1

4

128 × 128

39.0091

0.9269

12.6583

8.7147

0.9449

0.01

4

128 × 128

39.0488

0.9322

12.7041

8.8514

0.9450

0.001

4

128 × 128

39.2985

0.9348

12.1268

8.4724

0.9560

0.0001

4

128 × 128

39.1779

0.9335

12.6128

8.6061

0.9466

0.1

4

256 × 256

38.4313

0.9248

12.1535

7.5097

0.9423

0.01

4

256 × 256

38.5040

0.9262

12.1042

7.5257

0.9433

0.001

4

256 × 256

38.9427

0.9332

11.5610

7.1167

0.9491

0.0001

4

256 × 256

38.5252

0.9261

12.1132

7.4496

0.9433