Image 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 |
|---|---|---|
| loformer-local-frequency-transformer-for | 34.09 | 0.969 |
| deblurgan-v2-deblurring-orders-of-magnitude | 29.55 | 0.925 |
| irnext-rethinking-convolutional-network | 33.16 | 0.962 |
| banet-blur-aware-attention-networks-for | - | 0.957 |
| revisiting-global-statistics-aggregation-for | 33.08 | 0.962 |
| bringing-alive-blurred-moments | 30.58 | 0.941 |
| multi-outputs-is-all-you-need-for-deblur | 33.75 | 0.967 |
| dynamic-scene-deblurring-with-parameter | 31.58 | 0.9478 |
| deep-stacked-hierarchical-multi-patch-network | 31.50 | 0.9483 |
| revisiting-global-statistics-aggregation-for | 33.57 | 0.966 |
| hierarchical-information-flow-for-generalized | 33.99 | - |
| adarevd-adaptive-patch-exiting-reversible-1 | 34.6 | 0.972 |
| maxim-multi-axis-mlp-for-image-processing | 32.86 | - |
| multi-temporal-recurrent-neural-networks-for | 31.15 | 0.945 |
| mr-vnet-media-restoration-using-volterra | 34.04 | 0.969 |
| motion-aware-double-attention-network-for | 33.84 | 0.964 |
| deep-residual-fourier-transformation-for | 33.52 | 0.965 |
| restormer-efficient-transformer-for-high | 32.92 | 0.961 |
| 模型 19 | 30.12 | 0.9021 |
| simple-baselines-for-image-restoration | 33.69 | 0.967 |
| self-supervised-non-uniform-kernel-estimation | 34.06 | 0.968 |
| deep-multi-scale-convolutional-neural-network | 29.08 | 0.9135 |
| deblurring-by-realistic-blurring | 31.10 | 0.9424 |
| spatially-attentive-patch-hierarchical | 32.02 | 0.953 |
| blur-more-to-deblur-better-multi-blur2deblur | 32.16 | 0.953 |
| learning-event-based-motion-deblurring | 31.79 | 0.949 |
| mair-a-locality-and-continuity-preserving | 33.69 | - |
| a-mountain-shaped-single-stage-network-for | 33.74 | 0.967 |
| deblurgan-v2-deblurring-orders-of-magnitude | 28.17 | - |
| prompt-based-all-in-one-image-restoration | 33.74 | 0.967 |
| scale-recurrent-network-for-deep-image | - | 0.9342 |
| image-restoration-via-frequency-selection | 33.29 | 0.963 |
| efficient-and-explicit-modelling-of-image | 33.93 | 0.968 |
| revisiting-global-statistics-aggregation-for | 33.31 | 0.964 |
| dark-and-bright-channel-prior-embedded | 31.10 | 0.945 |
| aggregating-local-and-global-features-via | 34.05 | 0.969 |
| revisiting-image-deblurring-with-an-efficient | 33.72 | 0.967 |
| instruct-ipt-all-in-one-image-processing-1 | 33.86 | 0.967 |
| uformer-a-general-u-shaped-transformer-for | 32.97 | 0.967 |
| mixed-hierarchy-network-for-image-restoration | 33.04 | - |
| efficient-visual-state-space-model-for-image | 34.5 | 0.9712 |
| exploring-the-potential-of-channel | 33.28 | 0.963 |
| learning-degradation-representations-for | 33.28 | 0.964 |
| revitalizing-convolutional-network-for-image | 33.28 | 0.963 |
| efficient-spatio-temporal-recurrent-neural-1 | 31.07 | 0.9023 |
| efficient-frequency-domain-based-transformers | 34.21 | 0.969 |
| spatially-adaptive-residual-networks-for | 32.15 | 0.9560 |
| sdwnet-a-straight-dilated-network-with | 31.36 | - |
| rethinking-coarse-to-fine-approach-in-single | 32.68 | 0.959 |
| cascadedgaze-efficiency-in-global-context | 33.77 | 0.968 |
| spatio-temporal-filter-adaptive-network-for | 28.59 | 0.861 |
| image-restoration-with-mean-reverting | 30.7 | 0.901 |
| deblurgan-v2-deblurring-orders-of-magnitude | 28.03 | 0.922 |
| multi-stage-progressive-image-restoration | 32.66 | 0.959 |