Noise Estimation On Sidd

Average KL Divergence

PSNR Gap

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Average KL Divergence	PSNR Gap	Paper Title
GRDN	0.443	2.28	GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling
CBDNet	0.728	8.30	Toward Convolutional Blind Denoising of Real Photographs
PNGAN	0.153	0.84	Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
ULRD	0.545	4.90	Unprocessing Images for Learned Raw Denoising
DANet	0.212	2.06	Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation

0 of 5 row(s) selected.