Noise2Self: Blind Denoising by Self-Supervision

30 Jan 2019 Joshua Batson Loic Royer

We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement, while the true signal exhibits some correlation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Color Image Denoising CellNet DnCNN (n2t) PSNR 34.4 # 1
Color Image Denoising Hanzi DnCNN (n2t) PSNR 13.9 # 1
Color Image Denoising ImageNet DnCNN (n2t) PSNR 22 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet