HyperAI초신경

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

한국어

HyperAI초신경

Single Image Deraining On Test2800

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
MPRNet	33.64	0.938	Multi-Stage Progressive Image Restoration
UMRL	29.97	0.905	Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
RESCAN	31.29	0.904	Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining	-
MSPFN	32.82	0.930	Multi-Scale Progressive Fusion Network for Single Image Deraining
Restormer	34.18	0.944	Restormer: Efficient Transformer for High-Resolution Image Restoration
PreNet	-	0.916	Progressive Image Deraining Networks: A Better and Simpler Baseline
SEMI	24.43	0.782	Semi-supervised Transfer Learning for Image Rain Removal
DIDMDN	28.13	0.867	Density-aware Single Image De-raining using a Multi-stream Dense Network
KBNet	34.19	0.944	KBNet: Kernel Basis Network for Image Restoration
MAXIM	33.80	-	MAXIM: Multi-Axis MLP for Image Processing
DerainNet	24.31	0.861	Clearing the Skies: A deep network architecture for single-image rain removal
HINet	33.91	0.941	HINet: Half Instance Normalization Network for Image Restoration

0 of 12 row(s) selected.