Image Super Resolution On Urban100 4X

Métriques

PSNR

SSIM

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	PSNR	SSIM	Paper Title	Repository
BSRN	26.03	0.7835	Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
SRNTT-l2	25.5	-	Image Super-Resolution by Neural Texture Transfer
NLRN	25.79	0.7729	Non-Local Recurrent Network for Image Restoration
DBPN-RES-MR64-3	27.08	0.814	Deep Back-Projection Networks for Single Image Super-resolution
HAT_FIR	28.43	-	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
IDN	25.41	0.7632	Fast and Accurate Single Image Super-Resolution via Information Distillation Network
LapSRN	25.21	0.756	Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
HAN+	27.02	0.8131	Single Image Super-Resolution via a Holistic Attention Network
HBPN	27.3	0.818	Hierarchical Back Projection Network for Image Super-Resolution
SwinIR	27.45	0.8254	SwinIR: Image Restoration Using Swin Transformer
CSNLN	27.22	0.8168	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
SRGAN + Residual-in-Residual Dense Block	27.03	0.8153	ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
SwinIR (DUKD)	26.43	0.7972	Data Upcycling Knowledge Distillation for Image Super-Resolution
PixelRL-SR	23.28	0.7517	Multi-Step Reinforcement Learning for Single Image Super-Resolution
SwinOIR	26.74	0.806	Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
HMA†	28.69	0.8512	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
RDN	26.61	0.8028	Residual Dense Network for Image Super-Resolution
MWCNN	26.27	0.7890	Multi-level Wavelet-CNN for Image Restoration
MaIR+	27.89	0.8336	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration	-
ENet-E	25.66	0.7703	EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis

0 of 64 row(s) selected.