Image Super Resolution On Set5 2X Upscaling

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
RED30	37.66	0.9599	Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
c-DCSCN	37.13	.9569	Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
VDSR [[Kim et al.2016a]]	37.53	-	Accurate Image Super-Resolution Using Very Deep Convolutional Networks
DRCT-L	39.14	0.9658	DRCT: Saving Image Super-resolution away from Information Bottleneck
HAT	38.73	0.9637	Activating More Pixels in Image Super-Resolution Transformer
HBPN	38.13	0.961	Hierarchical Back Projection Network for Image Super-Resolution
CPAT	38.68	0.9633	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
DnCNN-3	37.58	-	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
ML-CrAIST	38.19	0.9617	ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer
N3Net	37.57	-	Neural Nearest Neighbors Networks
FACD	38.242	-	Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution	-
DBPN-RES-MR64-3	38.08	0.96	Deep Back-Projection Networks for Single Image Super-resolution
MaIR+	38.62	0.963	MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration	-
PMRN+	38.22	0.9612	Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution	-
SwinOIR	38.21	0.9614	Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
IMDN	38.00	-	Lightweight Image Super-Resolution with Information Multi-distillation Network
CPAT+	38.72	0.9635	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
DRCT	38.72	0.9646	DRCT: Saving Image Super-resolution away from Information Bottleneck
Deep CNN Denoiser	35.05	-	Learning Deep CNN Denoiser Prior for Image Restoration
HyperRes	36.69	0.94	Hypernetwork-Based Adaptive Image Restoration

0 of 41 row(s) selected.