Accurate and Fast Image Denoising via Attention Guided Scaling
- 9 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 6255-6265
Abstract
Image denoising is a classical topic yet still a challenging problem, especially for reducing noise from the texture information. Feature scaling (e.g., downscale and upscale) is a widely practice in image denoising to enlarge receptive field size and save resources. However, such a common operation would lose some visual informative details. To address those problems, we propose fast and accurate image denoising via attention guided scaling (AGS). We find that the main informative feature channel and visual primitives during the scaling should keep similar. We then propose to extract the global channel-wise attention to maintain main channel information. Moreover, we propose to collect global descriptors by considering the entire spatial feature. And we then distribute the global descriptors to local positions of the scaled feature, based on their specific needs. We further introduce AGS for adversarial training, resulting in a more powerful discriminator. Extensive experiments show the effectiveness of our proposed method, where we clearly surpass all the state-of-the-art methods on most popular synthetic and real-world denoising benchmarks quantitatively and visually. We further show that our network contributes to other high-level vision applications and improves their performances significantly.Keywords
Funding Information
- Northeastern University
This publication has 31 references indexed in Scilit:
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image RestorationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- Bilinear CNN Models for Fine-Grained Visual Recognition2015
- Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks2015
- Single image super-resolution from transformed self-exemplars2015
- Multiscale Image Blind DenoisingIEEE Transactions on Image Processing, 2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002