Image Super Resolution On Bsd100 3X Upscaling

Metrics

PSNR

Results

Performance results of various models on this benchmark

Model Name	PSNR	Paper Title	Repository
IMDN	29.09	Lightweight Image Super-Resolution with Information Multi-distillation Network
CPAT	29.56	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
Hi-IR-L	29.67	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
HAT	29.59	Activating More Pixels in Image Super-Resolution Transformer
CPAT+	29.59	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
SRFBN	29.24	Feedback Network for Image Super-Resolution
RED30	28.93	Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
SwinOIR	29.27	Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
MWCNN	29.12	Multi-level Wavelet-CNN for Image Restoration
DRLN+	29.4	Densely Residual Laplacian Super-Resolution
LCSCNet	28.87	LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution
RC-Net	28.76	Image Restoration Using Deep Regulated Convolutional Networks
CSNLN	29.33	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
HAN+	29.41	Single Image Super-Resolution via a Holistic Attention Network
HMA†	29.66	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
LTE	29.39	Local Texture Estimator for Implicit Representation Function
DnCNN-3	28.85	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
LFFN-S	28.91	Lightweight Feature Fusion Network for Single Image Super-Resolution
HAT_FIR	29.6	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
HAT-L	29.63	Activating More Pixels in Image Super-Resolution Transformer

0 of 21 row(s) selected.