HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Image Super Resolution On Urban100 4X

Metrics

PSNR
SSIM

Results

Performance results of various models on this benchmark

Model Name
PSNR
SSIM
Paper TitleRepository
BSRN26.030.7835Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
SRNTT-l225.5-Image Super-Resolution by Neural Texture Transfer
NLRN25.790.7729Non-Local Recurrent Network for Image Restoration
DBPN-RES-MR64-327.080.814Deep Back-Projection Networks for Single Image Super-resolution
HAT_FIR28.43-SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
IDN25.410.7632Fast and Accurate Single Image Super-Resolution via Information Distillation Network
LapSRN25.210.756Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
HAN+27.020.8131Single Image Super-Resolution via a Holistic Attention Network
HBPN27.30.818Hierarchical Back Projection Network for Image Super-Resolution
SwinIR27.450.8254 SwinIR: Image Restoration Using Swin Transformer
CSNLN27.220.8168Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
SRGAN + Residual-in-Residual Dense Block27.030.8153ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
SwinIR (DUKD)26.430.7972Data Upcycling Knowledge Distillation for Image Super-Resolution
PixelRL-SR23.280.7517Multi-Step Reinforcement Learning for Single Image Super-Resolution
SwinOIR26.740.806Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
HMA†28.690.8512HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
RDN26.610.8028Residual Dense Network for Image Super-Resolution
MWCNN26.270.7890Multi-level Wavelet-CNN for Image Restoration
MaIR+27.890.8336MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration-
ENet-E25.660.7703EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
0 of 64 row(s) selected.