Image Super Resolution On Set5 3X Upscaling

Metrics

PSNR

Results

Performance results of various models on this benchmark

Model Name	PSNR	Paper Title	Repository
IMDN	34.36	Lightweight Image Super-Resolution with Information Multi-distillation Network	-
SRFBN	34.70	Feedback Network for Image Super-Resolution	-
HMA†	35.35	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution	-
DRCT	35.18	DRCT: Saving Image Super-resolution away from Information Bottleneck	-
LFFN-S	34.04	Lightweight Feature Fusion Network for Single Image Super-Resolution	-
LCSCNet	33.99	LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution	-
Deep CNN Denoiser	31.26	Learning Deep CNN Denoiser Prior for Image Restoration	-
CSNLN	34.74	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining	-
Hi-IR-L	35.2	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
ML-CrAIST	34.7	ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer	-
AdaFM-Net	34.34	Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers	-
FACD	34.729	Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution	-
HAT_FIR	35.21	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution	-
DRCT-L	35.32	DRCT: Saving Image Super-resolution away from Information Bottleneck	-
DnCNN-3	33.75	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising	-
SwinFIR	35.15	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution	-
PMRN+	34.65	Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution	-
HAT	35.16	Activating More Pixels in Image Super-Resolution Transformer	-
RED30	33.82	Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections	-
MWCNN	34.17	Multi-level Wavelet-CNN for Image Restoration	-

0 of 32 row(s) selected.