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

Conventionally, image denoising and high-level vision tasks are handled separately in computer vision, and their connection is fragile. In this paper, we cope with the two jointly and explore the mutual influence between them with the focus on two questions, namely (1) how image denoising can help solving high-level vision problems, and (2) how the semantic information from high-level vision tasks can be used to guide image denoising. First we propose a deep convolutional neural network for image denoising which is able to outperform the state-of-the-art. Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and propose the use of joint loss for updating only the denoising network to allow the semantic information flowing into the optimization of the denoising network via back-propagation. Our experimental results demonstrate that on one hand, the proposed architecture is able to overcome the performance degradation of different high-level vision tasks, e.g., image classification and semantic segmentation, due to image noise or artifacts caused by conventional denoising approaches such as over-smoothing. On the other hand, with the guidance of high-level vision information, the denoising network can further preserve more fine details and generate more visually appealing results. To the best of our knowledge, this is the first work to systematically investigate the benefit of using high-level vision semantics for image denoising via deep learning.