External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising

Abstract

Most of existing image denoising methods learn image priors from either external data or the noisy image itself to remove noise. However, priors learned from external data may not be adaptive to the image to be denoised, while priors learned from the given noisy image may not be accurate due to the interference of corrupted noise. Meanwhile, the noise in real-world noisy images is very complex, which is hard to be described by simple distributions such as Gaussian distribution, making real-world noisy image denoising a very challenging problem. We propose to exploit the information in both external data and the given noisy image, and develop an external prior guided internal prior learning method for real-world noisy image denoising. We first learn external priors from an independent set of clean natural images. With the aid of learned external priors, we then learn internal priors from the given noisy image to refine the prior model. The external and internal priors are formulated as a set of orthogonal dictionaries to efficiently reconstruct the desired image. Extensive experiments are performed on several real-world noisy image datasets. The proposed method demonstrates highly competitive denoising performance, outperforming state-of-the-art denoising methods including those designed for real-world noisy images.

14 pages, 13figures, IEEE Trans. Image Processing 27(6): 2996-3010 (2018)

References in corpus (4)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Adaptive Image Denoising by Targeted Databases
• On learning optimized reaction diffusion processes for effective image restoration
• Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising

Cited by in corpus (23)

• STAR: A Structure and Texture Aware Retinex Model
• Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
• Real-world Noisy Image Denoising: A New Benchmark
• Conditional Variational Image Deraining
• NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoising
• Color Image and Multispectral Image Denoising Using Block Diagonal Representation
• Deep Learning on Image Denoising: An overview
• Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
• When AWGN-based Denoiser Meets Real Noises
• Multi-band Weighted $l_p$ Norm Minimization for Image Denoising
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes
• Spatial-Adaptive Network for Single Image Denoising
• Low-light Image Restoration with Short- and Long-exposure Raw Pairs
• Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
• Scaled Simplex Representation for Subspace Clustering
• Optimal Combination of Image Denoisers
• Joint group and residual sparse coding for image compressive sensing
• Human-Aware Motion Deblurring
• An Integrated Enhancement Solution for 24-hour Colorful Imaging
• Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool
• Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
• Learning Deep Image Priors for Blind Image Denoising