CVJan 6, 2017

Deep Class Aware Denoising

arXiv:1701.01698v211 citations
Originality Incremental advance
AI Analysis

This addresses the need for better image quality in mobile devices, though it is incremental by building on existing classifiers and denoising methods.

The paper tackles image denoising by incorporating semantic class awareness, showing that fine-tuning a denoiser for specific image classes improves reconstruction quality by up to 0.4 dB PSNR.

The increasing demand for high image quality in mobile devices brings forth the need for better computational enhancement techniques, and image denoising in particular. At the same time, the images captured by these devices can be categorized into a small set of semantic classes. However simple, this observation has not been exploited in image denoising until now. In this paper, we demonstrate how the reconstruction quality improves when a denoiser is aware of the type of content in the image. To this end, we first propose a new fully convolutional deep neural network architecture which is simple yet powerful as it achieves state-of-the-art performance even without being class-aware. We further show that a significant boost in performance of up to $0.4$ dB PSNR can be achieved by making our network class-aware, namely, by fine-tuning it for images belonging to a specific semantic class. Relying on the hugely successful existing image classifiers, this research advocates for using a class-aware approach in all image enhancement tasks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes