Natural Image Noise Dataset

Abstract

Convolutional neural networks have been the focus of research aiming to solve image denoising problems, but their performance remains unsatisfactory for most applications. These networks are trained with synthetic noise distributions that do not accurately reflect the noise captured by image sensors. Some datasets of clean-noisy image pairs have been introduced but they are usually meant for benchmarking or specific applications. We introduce the Natural Image Noise Dataset (NIND), a dataset of DSLR-like images with varying levels of ISO noise which is large enough to train models for blind denoising over a wide range of noise. We demonstrate a denoising model trained with the NIND and show that it significantly outperforms BM3D on ISO noise from unseen images, even when generalizing to images from a different type of camera. The Natural Image Noise Dataset is published on Wikimedia Commons such that it remains open for curation and contributions. We expect that this dataset will prove useful for future image denoising applications.

arXiv commentNTIRE at CVPR 2019

References in corpus (5)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Noise2Noise: Learning Image Restoration without Clean Data
• RENOIR - A Dataset for Real Low-Light Image Noise Reduction

Cited by in corpus (2)

• On the Importance of Denoising when Learning to Compress Images
• Toward Interactive Modulation for Photo-Realistic Image Restoration