HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Single Image Deraining On Test1200

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
M3SNet	33.52	0.925	A Mountain-Shaped Single-Stage Network for Accurate Image Restoration
MHNet	33.41	0.924	Mixed Hierarchy Network for Image Restoration
UMRL	-	0.910	Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
MPRNet	32.91	0.916	Multi-Stage Progressive Image Restoration
MAXIM	-	0.922	MAXIM: Multi-Axis MLP for Image Processing
MSPFN	32.39	0.916	Multi-Scale Progressive Fusion Network for Single Image Deraining
SEMI	26.05	0.822	Semi-supervised Transfer Learning for Image Rain Removal
DerainNet	-	0.835	Clearing the Skies: A deep network architecture for single-image rain removal
KBNet	33.82	0.931	KBNet: Kernel Basis Network for Image Restoration
DIDMDN	-	0.901	Density-aware Single Image De-raining using a Multi-stream Dense Network
Restormer	33.19	0.926	Restormer: Efficient Transformer for High-Resolution Image Restoration
RESCAN	-	0.882	Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining	-
HINet	33.05	0.919	HINet: Half Instance Normalization Network for Image Restoration
CAPTNet	34.77	0.937	Prompt-based Ingredient-Oriented All-in-One Image Restoration

0 of 14 row(s) selected.