HyperAI超神经

Image Super Resolution On Set14 4X Upscaling

评估指标

PSNR
SSIM

评测结果

各个模型在此基准测试上的表现结果

模型名称
PSNR
SSIM
Paper TitleRepository
ATD29.240.7974Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
Manifold Simplification28.800.7856Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
BSRN28.560.7803Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
HBPN28.670.785Hierarchical Back Projection Network for Image Super-Resolution
Extracter-rec28.090.782EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution
HMA†29.510.8019HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
ENet-E28.420.7774EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
SPSR26.640.7930Structure-Preserving Super Resolution with Gradient Guidance
MaIR29.20.7958MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration-
ProSR28.94-A Fully Progressive Approach to Single-Image Super-Resolution
CRAFT28.850.7872Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
SESR28.320.784SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
AESOP27.4210.7438Auto-Encoded Supervision for Perceptual Image Super-Resolution
GMFN28.840.7888Gated Multiple Feedback Network for Image Super-Resolution
CPAT29.340.7991Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution-
bicubic-0.7486Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
SPMC27.570.76Detail-revealing Deep Video Super-resolution
4PP-EUSR27.62220.7419Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
Edge-informed SR25.190.894Edge-Informed Single Image Super-Resolution
S-RFN-0.7946Progressive Perception-Oriented Network for Single Image Super-Resolution
0 of 103 row(s) selected.