Image Super Resolution On Urban100 3X
평가 지표
PSNR
SSIM
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | PSNR | SSIM |
|---|---|---|
| swinfir-revisiting-the-swinir-with-fast | 30.43 | 0.8913 |
| hmanet-hybrid-multi-axis-aggregation-network | 31.00 | 0.8984 |
| activating-more-pixels-in-image-super | 30.70 | 0.8949 |
| hierarchical-information-flow-for-generalized | 31.07 | 0.902 |
| lightweight-image-super-resolution-with-1 | 28.17 | - |
| beyond-a-gaussian-denoiser-residual-learning | 27.15 | - |
| channel-partitioned-windowed-attention-and | 30.63 | 0.8934 |
| ml-craist-multi-scale-low-high-frequency | 28.73 | 0.8651 |
| single-image-super-resolution-via-a-holistic | 29.21 | 0.8710 |
| feedback-network-for-image-super-resolution | 28.73 | - |
| feature-based-adaptive-contrastive | 28.818 | - |
| pre-trained-image-processing-transformer | 29.49 | - |
| image-super-resolution-with-cross-scale-non | 29.13 | 0.8712 |
| lcscnet-linear-compressing-based-skip | 27.24 | - |
| local-texture-estimator-for-implicit | 29.41 | - |
| activating-more-pixels-in-image-super | 30.92 | 0.8981 |
| ml-craist-multi-scale-low-high-frequency | 28.89 | 0.8676 |
| a-framework-for-real-time-object-detection | 28.87 | 0.8674 |
| swinfir-revisiting-the-swinir-with-fast | 30.77 | - |
| channel-partitioned-windowed-attention-and | 30.52 | 0.8923 |
| multi-level-wavelet-cnn-for-image-restoration | 28.13 | - |
| densely-residual-laplacian-super-resolution | 29.37 | 0.8746 |