Image Super Resolution On Bsd100 4X Upscaling

Metrics

PSNR

SSIM

Results

Performance results of various models on this benchmark

Model Name	PSNR	SSIM	Paper Title	Repository
HAT	28.05	0.7534	Activating More Pixels in Image Super-Resolution Transformer
BSRN	27.57	0.7353	Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
ProSR	27.79	-	A Fully Progressive Approach to Single-Image Super-Resolution
DRCT-L	28.16	0.7577	DRCT: Saving Image Super-resolution away from Information Bottleneck
SPSR	25.505	0.6576	Structure-Preserving Super Resolution with Gradient Guidance
ZSSR	27.12	0.7211	"Zero-Shot" Super-Resolution using Deep Internal Learning
SRGAN	25.16	0.6688	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
CSNLN	27.8	0.7439	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
Manifold Simplification	27.66	0.7380	Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
SRResNet	27.58	0.762	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
DRCT	28.06	0.7533	DRCT: Saving Image Super-resolution away from Information Bottleneck
NLRN	27.48	0.7306	Non-Local Recurrent Network for Image Restoration
IMDN	27.56	-	Lightweight Image Super-Resolution with Information Multi-distillation Network
Config (e)	-	-	One-to-many Approach for Improving Super-Resolution
RDN	27.72	0.7419	Residual Dense Network for Image Super-Resolution
CPAT+	28.06	0.7532	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
RFN	27.83	-	Progressive Perception-Oriented Network for Single Image Super-Resolution
GMFN	27.74	0.7421	Gated Multiple Feedback Network for Image Super-Resolution
WaveMixSR-V2	27.87	0.764	WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
RL-CSC	27.44	0.7302	Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding	-

0 of 71 row(s) selected.