HyperAI초신경

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

한국어

HyperAI초신경

Jpeg Artifact Correction On Live1 Quality 10 1

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
Residual Dense Network +	29.7	0.8252	Residual Dense Network for Image Restoration
Hi-IR	29.94	0.8359	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
DnCNN-3	29.19	-	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
RED30	29.35	-	Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
HyperRes	28.81	0.82	Hypernetwork-Based Adaptive Image Restoration
MemNet	29.45	0.8327	MemNet: A Persistent Memory Network for Image Restoration
QGAC	29.53	0.840	Quantization Guided JPEG Artifact Correction
MWCNN	29.69	0.8357	Multi-level Wavelet-CNN for Image Restoration
ARCNN	29.11	0.8235	Compression Artifacts Reduction by a Deep Convolutional Network
FBCNN	29.75	0.827	Towards Flexible Blind JPEG Artifacts Removal
DPW-SDNet	29.40	0.8235	DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images	-
IDCN	29.71	0.838	Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction	-
S-Net	29.44	0.8325	S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction	-

0 of 13 row(s) selected.