Real-world Noisy Image Denoising: A New Benchmark

Abstract

Most of previous image denoising methods focus on additive white Gaussian noise (AWGN). However,the real-world noisy image denoising problem with the advancing of the computer vision techiniques. In order to promote the study on this problem while implementing the concurrent real-world image denoising datasets, we construct a new benchmark dataset which contains comprehensive real-world noisy images of different natural scenes. These images are captured by different cameras under different camera settings. We evaluate the different denoising methods on our new dataset as well as previous datasets. Extensive experimental results demonstrate that the recently proposed methods designed specifically for realistic noise removal based on sparse or low rank theories achieve better denoising performance and are more robust than other competing methods, and the newly proposed dataset is more challenging. The constructed dataset of real photographs is publicly available at \url{https://github.com/csjunxu/PolyUDataset} for researchers to investigate new real-world image denoising methods. We will add more analysis on the noise statistics in the real photographs of our new dataset in the next version of this article.

arXiv comment13 pages, 8 figures, 8 tables. arXiv admin note: text overlap with arXiv:1707.01313 by other authors

References in corpus (5)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• RENOIR - A Dataset for Real Low-Light Image Noise Reduction
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• 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 (30)

• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Color Image and Multispectral Image Denoising Using Block Diagonal Representation
• Quaternion Nuclear Norm minus Frobenius Norm Minimization for color image reconstruction
• UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
• Bilateral Spectrum Weighted Total Variation for Noisy-Image Super-Resolution and Image Denoising
• Deep Learning on Image Denoising: An overview
• Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
• Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images
• A CNN-Based Blind Denoising Method for Endoscopic Images
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Designing and Training of A Dual CNN for Image Denoising
• OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers
• Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes
• Spatial-Adaptive Network for Single Image Denoising
• Monitoring and Adapting the Physical State of a Camera for Autonomous Vehicles
• Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
• Deep Learning with Inaccurate Training Data for Image Restoration
• Learning an Adaptive Model for Extreme Low-light Raw Image Processing
• View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution
• Learning Model-Blind Temporal Denoisers without Ground Truths
• Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
• Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition
• Identity Enhanced Residual Image Denoising
• Dynamic Low-light Imaging with Quanta Image Sensors
• Learning Deep Image Priors for Blind Image Denoising
• Enhancing and Learning Denoiser without Clean Reference