HyperAI초신경

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

한국어

HyperAI초신경

Deblurring On Realblur J 1

평가 지표

PSNR (sRGB)

Params(M)

SSIM (sRGB)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR (sRGB)	Params(M)	SSIM (sRGB)	Paper Title	Repository
MAXIM	32.84	22.2	0.935	MAXIM: Multi-Axis MLP for Image Processing
SRN	31.38	8.06	0.909	Scale-recurrent Network for Deep Image Deblurring
DeblurGAN-v2	29.69	5.08	0.870	DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
MPRNet	31.76	20.1	0.922	Multi-Stage Progressive Image Restoration
LoFormer	32.90	-	0.933	LoFormer: Local Frequency Transformer for Image Deblurring
Stripformer	32.48	20	0.929	Stripformer: Strip Transformer for Fast Image Deblurring
DeepRFT+	32.63	-	0.933	Intriguing Findings of Frequency Selection for Image Deblurring
AdaRevD	33.96	-	0.944	AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
BANet	32.00	-	0.923	BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
ID-Blau (Restormer)	33.11	-	0.937	ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
MLWNet	33.84	-	0.941	Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
MSSNet	32.1	15.6	0.928	MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
MIMO-UNet++	32.05	16.1	0.921	Rethinking Coarse-to-Fine Approach in Single Image Deblurring
ALGNet	32.94	-	0.946	Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring
FFTformer	32.62	-	0.9326	Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
ID-Blau (Stripformer)	33.77	20	0.940	ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
ID-Blau (FFTformer)	32.88	-	0.934	ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation

0 of 17 row(s) selected.