Image Super Resolution On Bsd100 2X Upscaling

Metrics

PSNR

Results

Performance results of various models on this benchmark

Model Name	PSNR	Paper Title	Repository
MWCNN	32.23	Multi-level Wavelet-CNN for Image Restoration	-
SwinFIR	32.64	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution	-
Hi-IR-L	32.77	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
CARN [[Ahn et al.2018]]	32.09	Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network	-
DnCNN-3	31.9	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising	-
HAT-L	32.74	Activating More Pixels in Image Super-Resolution Transformer	-
WaveMixSR-V2	33.12	WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency	-
FALSR-A	32.12	Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search	-
RED30	31.99	Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections	-
IMDN	32.19	Lightweight Image Super-Resolution with Information Multi-distillation Network	-
CPAT	32.64	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
DRCT-L	32.90	DRCT: Saving Image Super-resolution away from Information Bottleneck	-
LTE	32.44	Local Texture Estimator for Implicit Representation Function	-
HAT_FIR	32.71	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution	-
SwinOIR	32.34	Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy	-
SRFBN	32.29	Feedback Network for Image Super-Resolution	-
CSNLN	32.4	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining	-
IPT	32.48	Pre-Trained Image Processing Transformer	-
FSRCNN [[Dong et al.2016]]	31.53	Accelerating the Super-Resolution Convolutional Neural Network	-
HMA†	32.79	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution	-

0 of 30 row(s) selected.