When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach

TL;DR

This paper introduces a deep learning framework that jointly performs image denoising and high-level vision tasks, demonstrating mutual benefits where denoising improves high-level task performance and high-level guidance enhances denoising results.

Contribution

It proposes a novel deep neural network architecture that integrates image denoising with high-level vision tasks, a first in exploring their mutual influence using deep learning.

Findings

The denoising network achieves state-of-the-art performance.

Joint training improves high-level vision task robustness.

High-level guidance produces more visually appealing denoising results.

Abstract

Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural network for image denoising which achieves the state-of-the-art performance. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation. We demonstrate that on one hand, the proposed denoiser has the generality to overcome the performance degradation of different high-level vision tasks. On the other hand, with the guidance of high-level vision information, the denoising network can generate more visually appealing results. To the best of our knowledge, this is the first work investigating the benefit of exploiting image semantics simultaneously for image denoising and high-level vision tasks via deep learning. The code is available online https://github.com/Ding-Liu/DeepDenoising.