Image Super Resolution On Manga109 4X

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
HMA†	33.19	0.9344	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
DRCT-L	33.14	0.9347	DRCT: Saving Image Super-resolution away from Information Bottleneck
Hi-IR-L	33.13	0.9366	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
HAT-L	33.09	0.9335	Activating More Pixels in Image Super-Resolution Transformer
HAT_FIR	33.03	-	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
DRCT	32.96	0.9324	DRCT: Saving Image Super-resolution away from Information Bottleneck
HAT	32.87	0.9319	Activating More Pixels in Image Super-Resolution Transformer
CPAT+	32.85	0.9318	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
SwinFIR	32.83	0.9314	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
RGT+	32.68	0.9303	Recursive Generalization Transformer for Image Super-Resolution
DAT+	32.67	0.9301	Dual Aggregation Transformer for Image Super-Resolution
MaIR+	32.66	0.9297	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
DAT	32.51	0.9291	Dual Aggregation Transformer for Image Super-Resolution
RGT	32.50	0.9291	Recursive Generalization Transformer for Image Super-Resolution
MaIR	32.46	0.9284	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
SwinIR	32.22	0.9273	SwinIR: Image Restoration Using Swin Transformer
ABPN	31.79	0.921	Image Super-Resolution via Attention based Back Projection Networks
DRLN+	31.78	0.9211	Densely Residual Laplacian Super-Resolution
+SPN	31.75	0.9229	Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
DBPN-RES-MR64-3	31.74	0.921	Deep Back-Projection Networks for Single Image Super-resolution

0 of 49 row(s) selected.