HyperAI초신경

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

한국어

HyperAI초신경

Single Image Deraining On Rain100L

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
IPT	41.62	0.988	Pre-Trained Image Processing Transformer
MCW-Net	39.73	0.988	MCW-Net: Single Image Deraining with Multi-level Connections and Wide Regional Non-local Blocks
CAPTNet	39.22	0.981	Prompt-based Ingredient-Oriented All-in-One Image Restoration
PReNet	37.48	0.979	Progressive Image Deraining Networks: A Better and Simpler Baseline
MPRNet	36.40	0.965	Multi-Stage Progressive Image Restoration
MAXIM	-	0.977	MAXIM: Multi-Axis MLP for Image Processing
Instruct-IPT	39.35	0.977	Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
MSPFN	32.40	0.933	Multi-Scale Progressive Fusion Network for Single Image Deraining
M3SNet	40.04	0.985	A Mountain-Shaped Single-Stage Network for Accurate Image Restoration
HINet	37.28	0.97	HINet: Half Instance Normalization Network for Image Restoration
RESCAN	-	0.881	Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining	-
MHNet	39.47	0.984	Mixed Hierarchy Network for Image Restoration
SEMI	25.03	0.842	Semi-supervised Transfer Learning for Image Rain Removal
DerainNet	-	0.884	Clearing the Skies: A deep network architecture for single-image rain removal
IR-SDE	38.3	0.9805	Image Restoration with Mean-Reverting Stochastic Differential Equations
UMRL	-	0.923	Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
SFNet	38.21	0.974	Selective Frequency Network for Image Restoration
Restormer	38.99	0.978	Restormer: Efficient Transformer for High-Resolution Image Restoration
DIDMDN	-	0.741	Density-aware Single Image De-raining using a Multi-stream Dense Network

0 of 19 row(s) selected.