OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers

Abstract

Image denoising has recently taken a leap forward due to machine learning. However, image denoisers, both expert-based and learning-based, are mostly tested on well-behaved generated noises (usually Gaussian) rather than on real-life noises, making performance comparisons difficult in real-world conditions. This is especially true for learning-based denoisers which performance depends on training data. Hence, choosing which method to use for a specific denoising problem is difficult. This paper proposes a comparative study of existing denoisers, as well as an extensible open tool that makes it possible to reproduce and extend the study. MWCNN is shown to outperform other methods when trained for a real-world image interception noise, and additionally is the second least compute hungry of the tested methods. To evaluate the robustness of conclusions, three test sets are compared. A Kendall's Tau correlation of only 60% is obtained on methods ranking between noise types, demonstrating the need for a benchmarking tool.

References in corpus (5)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Noise2Noise: Learning Image Restoration without Clean Data
• Real-world Noisy Image Denoising: A New Benchmark
• Electro-Magnetic Side-Channel Attack Through Learned Denoising and Classification

Cited by in corpus (1)

• Electro-Magnetic Side-Channel Attack Through Learned Denoising and Classification