HyperAI초신경

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

한국어

HyperAI초신경

Single Image Deraining On Rain100H

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
HINet	30.65	0.894	HINet: Half Instance Normalization Network for Image Restoration
MSPFN	28.66	0.86	Multi-Scale Progressive Fusion Network for Single Image Deraining
MHNet	30.34	-	Mixed Hierarchy Network for Image Restoration
UMRL	-	0.832	Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
PReNet	29.46	0.899	Progressive Image Deraining Networks: A Better and Simpler Baseline
MPRNet	30.41	0.89	Multi-Stage Progressive Image Restoration
M3SNet	30.64	0.892	A Mountain-Shaped Single-Stage Network for Accurate Image Restoration
MAXIM	-	0.903	MAXIM: Multi-Axis MLP for Image Processing
GOUB (Mean-ODE)	34.56	0.9414	Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
DA-CLIP	33.91	0.926	Controlling Vision-Language Models for Multi-Task Image Restoration
RESCAN	26.36	0.786	Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining	-
IR-SDE	31.65	0.9041	Image Restoration with Mean-Reverting Stochastic Differential Equations
MCW-Net	30.70	0.922	MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks
Restormer	31.46	0.904	Restormer: Efficient Transformer for High-Resolution Image Restoration
DerainNet	-	0.592	Clearing the Skies: A deep network architecture for single-image rain removal
SEMI	16.56	0.486	Semi-supervised Transfer Learning for Image Rain Removal
DIDMDN	-	0.524	Density-aware Single Image De-raining using a Multi-stream Dense Network

0 of 17 row(s) selected.