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

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.

the 27th International Joint Conference on Artificial Intelligence (2018)

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Studying Very Low Resolution Recognition Using Deep Networks
• Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
• On the Relation between Color Image Denoising and Classification

Cited by in corpus (15)

• A Review on Deep Learning in Medical Image Reconstruction
• An All-in-One Network for Dehazing and Beyond
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• TBC-Net: A real-time detector for infrared small target detection using semantic constraint
• Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
• Deep Learning on Image Denoising: An overview
• When AWGN-based Denoiser Meets Real Noises
• Improving Robustness of Deep-Learning-Based Image Reconstruction
• Segmentation-Aware Image Denoising without Knowing True Segmentation
• A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
• FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification
• The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling
• Deep joint rain and haze removal from single images
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration
• DAVID: Dual-Attentional Video Deblurring