HyperAIHyperAI超神経
ホームニュース論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Image Super Resolution On Urban100 3X

評価指標

PSNR
SSIM

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
PSNR
SSIM
Paper TitleRepository
SwinFIR30.430.8913SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution-
HMA†31.000.8984HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution-
HAT30.700.8949Activating More Pixels in Image Super-Resolution Transformer-
Hi-IR-L31.070.902Hierarchical Information Flow for Generalized Efficient Image Restoration-
IMDN28.17-Lightweight Image Super-Resolution with Information Multi-distillation Network-
DnCNN-327.15-Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising-
CPAT+30.630.8934Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
ML-CrAIST-Li28.730.8651ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer-
HAN+29.210.8710Single Image Super-Resolution via a Holistic Attention Network-
SRFBN28.73-Feedback Network for Image Super-Resolution-
FACD28.818-Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution-
IPT29.49-Pre-Trained Image Processing Transformer-
CSNLN29.130.8712Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining-
LCSCNet27.24-LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution-
LTE29.41-Local Texture Estimator for Implicit Representation Function-
HAT-L30.920.8981Activating More Pixels in Image Super-Resolution Transformer-
ML-CrAIST28.890.8676ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer-
SwinOIR28.870.8674Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy-
HAT_FIR30.77-SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution-
CPAT30.520.8923Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
0 of 22 row(s) selected.