When AWGN-based Denoiser Meets Real Noises

6 Apr 2019Yuqian ZhouJianbo JiaoHaibin HuangYang WangJue WangHonghui ShiThomas Huang

Discriminative learning-based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). The synthetic noises adopted in most previous work are pixel-independent, but real noises are mostly spatially/channel-correlated and spatially/channel-variant... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Denoising Darmstadt Noise Dataset Pixel-shuffling Downsampling PSNR 38.4 # 1