Deblurring On Gopro
评估指标
PSNR
SSIM
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | PSNR | SSIM |
|---|---|---|
| spatio-temporal-filter-adaptive-network-for | 28.59 | 0.861 |
| spatially-attentive-patch-hierarchical | 32.02 | 0.953 |
| rethinking-coarse-to-fine-approach-in-single | 32.68 | 0.959 |
| vrt-a-video-restoration-transformer | 34.81 | 0.9724 |
| ghost-deblurgan-and-its-application-to | 28.75 | 0.919 |
| flow-guided-sparse-transformer-for-video | 33.03 | 0.964 |
| motion-aware-double-attention-network-for | 33.84 | 0.964 |
| deblurgan-v2-deblurring-orders-of-magnitude | 29.55 | 0.934 |
| deblurgan-v2-deblurring-orders-of-magnitude | 28.17 | 0.925 |
| deep-recurrent-neural-network-with-multi | 33.32 | 0.9627 |
| mssnet-multi-scale-stage-network-for-single | 32.02 | 0.953 |
| deep-multi-scale-convolutional-neural-network | 29.08 | 0.9135 |
| cascaded-deep-video-deblurring-using-temporal | 31.67 | 0.9279 |
| stripformer-strip-transformer-for-fast-image | 33.08 | 0.962 |
| revisiting-global-statistics-aggregation-for | 33.57 | 0.966 |
| id-blau-image-deblurring-by-implicit | 33.51 | 0.965 |
| banet-blur-aware-attention-networks-for | 32.54 | 0.957 |
| revisiting-global-statistics-aggregation-for | 33.08 | 0.962 |
| efficient-spatio-temporal-recurrent-neural-1 | 31.07 | 0.9023 |
| bringing-alive-blurred-moments | 30.58 | 0.941 |
| multi-stage-progressive-image-restoration | 32.66 | 0.959 |
| deblurring-by-realistic-blurring | 31.10 | 0.9424 |
| unsupervised-flow-aligned-sequence-to | 31.82 | 0.923 |
| id-blau-image-deblurring-by-implicit | 34.36 | 0.970 |
| revisiting-global-statistics-aggregation-for | 33.31 | 0.964 |
| revisiting-global-statistics-aggregation-for | 33.8 | 0.966 |
| scale-recurrent-network-for-deep-image | - | 0.9342 |
| deblurdinat-a-lightweight-and-effective | 33.63 | 0.967 |
| learning-event-based-motion-deblurring | 31.79 | 0.949 |
| neural-image-re-exposure | 35.03 | 0.973 |
| mefnet-multi-scale-event-fusion-network-for | 35.46 | 0.972 |
| mssnet-multi-scale-stage-network-for-single | 33.01 | 0.961 |
| efficient-multi-scale-network-with-learnable | 33.83 | 0.968 |
| dynamic-scene-deblurring-with-parameter | 31.58 | 0.9478 |
| simple-baselines-for-image-restoration | 33.69 | 0.967 |
| deblurgan-v2-deblurring-orders-of-magnitude | 28.03 | 0.922 |
| dark-and-bright-channel-prior-embedded | 31.10 | 0.945 |
| adarevd-adaptive-patch-exiting-reversible-1 | 34.6 | 0.972 |
| mssnet-multi-scale-stage-network-for-single | 33.39 | 0.964 |
| hinet-half-instance-normalization-network-for | 32.71 | - |
| deep-residual-fourier-transformation-for | 33.52 | 0.965 |
| learning-truncated-causal-history-model-for | 34.5 | 0.972 |
| multi-temporal-recurrent-neural-networks-for | 31.15 | 0.945 |
| restormer-efficient-transformer-for-high | 32.92 | 0.961 |
| selective-frequency-network-for-image | 33.27 | 0.963 |
| no-attention-is-needed-grouped-spatial | 35.88 | 0.979 |
| id-blau-image-deblurring-by-implicit | 33.66 | 0.966 |
| blur-more-to-deblur-better-multi-blur2deblur | 32.16 | 0.953 |
| deep-stacked-hierarchical-multi-patch-network | 31.50 | 0.9483 |
| maxim-multi-axis-mlp-for-image-processing | 32.86 | - |
| blur-aware-spatio-temporal-sparse-transformer | 35.98 | 0.9792 |
| spatially-adaptive-residual-networks-for | 32.15 | 0.9560 |
| uformer-a-general-u-shaped-transformer-for | 32.97 | 0.967 |
| spatio-temporal-deformable-attention-network | 32.29 | 0.9313 |
| deformable-convolutions-and-lstm-based | 35.61 | 0.973 |