Image Super Resolution On Set14 4X Upscaling

Metriken

PSNR

SSIM

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	PSNR	SSIM	Paper Title	Repository
ATD	29.24	0.7974	Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
Manifold Simplification	28.80	0.7856	Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
BSRN	28.56	0.7803	Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
HBPN	28.67	0.785	Hierarchical Back Projection Network for Image Super-Resolution
Extracter-rec	28.09	0.782	EXTRACTER: Efficient Texture Matching with Attention and Gradient Enhancing for Large Scale Image Super Resolution
HMA†	29.51	0.8019	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
ENet-E	28.42	0.7774	EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
SPSR	26.64	0.7930	Structure-Preserving Super Resolution with Gradient Guidance
MaIR	29.2	0.7958	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration	-
ProSR	28.94	-	A Fully Progressive Approach to Single-Image Super-Resolution
CRAFT	28.85	0.7872	Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution
SESR	28.32	0.784	SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
AESOP	27.421	0.7438	Auto-Encoded Supervision for Perceptual Image Super-Resolution
GMFN	28.84	0.7888	Gated Multiple Feedback Network for Image Super-Resolution
CPAT	29.34	0.7991	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
bicubic	-	0.7486	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
SPMC	27.57	0.76	Detail-revealing Deep Video Super-resolution
4PP-EUSR	27.6222	0.7419	Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
Edge-informed SR	25.19	0.894	Edge-Informed Single Image Super-Resolution
S-RFN	-	0.7946	Progressive Perception-Oriented Network for Single Image Super-Resolution

0 of 103 row(s) selected.