Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization

Abstract

Real-noise denoising is a challenging task because the statistics of real-noise do not follow the normal distribution, and they are also spatially and temporally changing. In order to cope with various and complex real-noise, we propose a well-generalized denoising architecture and a transfer learning scheme. Specifically, we adopt an adaptive instance normalization to build a denoiser, which can regularize the feature map and prevent the network from overfitting to the training set. We also introduce a transfer learning scheme that transfers knowledge learned from synthetic-noise data to the real-noise denoiser. From the proposed transfer learning, the synthetic-noise denoiser can learn general features from various synthetic-noise data, and the real-noise denoiser can learn the real-noise characteristics from real data. From the experiments, we find that the proposed denoising method has great generalization ability, such that our network trained with synthetic-noise achieves the best performance for Darmstadt Noise Dataset (DND) among the methods from published papers. We can also see that the proposed transfer learning scheme robustly works for real-noise images through the learning with a very small number of labeled data.

arXiv commentCVPR accepted paper. The paper will be updated according to reviewers' comments

References in corpus (6)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• RENOIR - A Dataset for Real Low-Light Image Noise Reduction
• Real-world Noisy Image Denoising: A New Benchmark
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising