Image Super Resolution On Set14 4X Upscaling

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

			Paper Title	Repository
DRCT-L	29.54	0.8025	DRCT: Saving Image Super-resolution away from Information Bottleneck
HMA†	29.51	0.8019	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
Hi-IR-L	29.49	0.8041	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
HAT-L	29.47	0.8015	Activating More Pixels in Image Super-Resolution Transformer
HAT_FIR	29.44	-	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
DRCT	29.40	0.8003	DRCT: Saving Image Super-resolution away from Information Bottleneck
HAT	29.38	0.8001	Activating More Pixels in Image Super-Resolution Transformer
CPAT+	29.36	0.7996	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
SwinFIR	29.36	0.7993	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
CPAT	29.34	0.7991	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
CFAT	29.30	0.7985	CFAT: Unleashing Triangular Windows for Image Super-resolution	-
DAT+	29.29	0.7983	Dual Aggregation Transformer for Image Super-Resolution
MaIR+	29.28	0.7974	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
RGT+	29.28	0.7979	Recursive Generalization Transformer for Image Super-Resolution
ATD	29.24	0.7974	Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
DAT	29.23	0.7973	Dual Aggregation Transformer for Image Super-Resolution
RGT	29.23	0.7972	Recursive Generalization Transformer for Image Super-Resolution
MaIR	29.2	0.7958	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
Contrast	29.20	0.7973	-	-
MambaIR	29.20	0.7961	MambaIR: A Simple Baseline for Image Restoration with State-Space Model

0 of 103 row(s) selected.