Image Dehazing On Sots Indoor

Métriques

PSNR

SSIM

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	PSNR	SSIM	Paper Title	Repository
FFA-Net	36.39	0.989	FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
DSANet	41.36	0.997	Dual-domain strip attention for image restoration
SANet	40.40	0.996	Strip Attention for Image Restoration
U2-Former	36.42	0.988	U2-Former: A Nested U-shaped Transformer for Image Restoration	-
EMRA-Net	25.72	0.9448	An ensemble multi-scale residual attention network (EMRA-net) for image Dehazing
PFDN	32.68	0.976	Physics-based Feature Dehazing Networks	-
CL2S	35.36	0.9808	Rethinking the Elementary Function Fusion for Single-Image Dehazing
GridDehazeNet	32.16	0.984	GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
AOD-Net	20.51	0.816	AOD-Net: All-In-One Dehazing Network
MAXIM-2S	38.11	-	MAXIM: Multi-Axis MLP for Image Processing
Uformer	31.91	0.971	Uformer: A General U-Shaped Transformer for Image Restoration
DehazeFormer-L	40.05	0.996	Vision Transformers for Single Image Dehazing
ConvIR	42.72	0.997	Revitalizing Convolutional Network for Image Restoration
GFN	22.30	0.880	Gated Fusion Network for Single Image Dehazing	-
AECR-Net	37.17	0.990	Contrastive Learning for Compact Single Image Dehazing
C2PNet	42.56	0.9954	Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
MixDehazeNet	42.62	0.997	MixDehazeNet : Mix Structure Block For Image Dehazing Network
Deep DCP	19.25	0.832	Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
DEA-Net-CR	41.31	0.9945	DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
IRNeXt	41.21	0.996	IRNeXt: Rethinking Convolutional Network Design for Image Restoration

0 of 33 row(s) selected.