LIDIA: Lightweight Learned Image Denoising with Instance Adaptation

Abstract

Image denoising is a well studied problem with an extensive activity that has spread over several decades. Despite the many available denoising algorithms, the quest for simple, powerful and fast denoisers is still an active and vibrant topic of research. Leading classical denoising methods are typically designed to exploit the inner structure in images by modeling local overlapping patches, while operating in an unsupervised fashion. In contrast, recent newcomers to this arena are supervised and universal neural-network-based methods that bypass this modeling altogether, targeting the inference goal directly and globally, while tending to be very deep and parameter heavy. This work proposes a novel lightweight learnable architecture for image denoising, and presents a combination of supervised and unsupervised training of it, the first aiming for a universal denoiser and the second for adapting it to the incoming image. Our architecture embeds in it several of the main concepts taken from classical methods, relying on patch processing, leveraging non-local self-similarity, exploiting representation sparsity and providing a multiscale treatment. Our proposed universal denoiser achieves near state-of-the-art results, while using a small fraction of the typical number of parameters. In addition, we introduce and demonstrate two highly effective ways for further boosting the denoising performance, by adapting this universal network to the input image.

References in corpus (10)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Noise2Noise: Learning Image Restoration without Clean Data
• Image Processing using Smooth Ordering of its Patches
• Class-Aware Fully-Convolutional Gaussian and Poisson Denoising
• Residual Dense Network for Image Restoration
• Solving Inverse Problems with Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
• Patch-Ordering as a Regularization for Inverse Problems in Image Processing
• Single Image Super Resolution - When Model Adaptation Matters

Cited by in corpus (11)

• DCT2net: an interpretable shallow CNN for image denoising
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• Joint Multi-Scale Tone Mapping and Denoising for HDR Image Enhancement
• Fast Scalable Image Restoration using Total Variation Priors and Expectation Propagation
• Adaptive Denoising via GainTuning
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
• Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
• SNIPS: Solving Noisy Inverse Problems Stochastically
• New Computational Techniques for a Faster Variation of BM3D Image Denoising
• Noise2Inpaint: Learning Referenceless Denoising by Inpainting Unrolling