Proceedings

Multi-Scale Selective Feedback Network with Dual Loss for Real Image Denoising

Xiaowan Hu, Yuanhao Cai, Zhihong Liu, Haoqian Wang, Yulun Zhang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 729-735.

https://doi.org/10.24963/ijcai.2021/101

Keywords

  • Computer Vision: Computational Photography, Photometry, Shape from X
  • Machine Learning: Deep Learning

Abstract

The feedback mechanism in the human visual system extracts high-level semantics from noisy scenes. It then guides low-level noise removal, which has not been fully explored in image denoising networks based on deep learning. The commonly used fully-supervised network optimizes parameters through paired training data. However, unpaired images without noise-free labels are ubiquitous in the real world. Therefore, we proposed a multi-scale selective feedback network (MSFN) with the dual loss. We allow shallow layers to access valuable contextual information from the following deep layers selectively between two adjacent time steps. Iterative refinement mechanism can remove complex noise from coarse to fine. The dual regression is designed to reconstruct noisy images to establish closed-loop supervision that is training-friendly for unpaired data. We use the dual loss to optimize the primary clean-to-noisy task and the dual noisy-to-clean task simultaneously. Extensive experiments prove that our method achieves state-of-the-art results and shows better adaptability on real-world images than the existing methods.

Xiaowan Hu, Yuanhao Cai, Zhihong Liu, Haoqian Wang, and Yulun Zhang. 2021. Multi-Scale Selective Feedback Network with Dual Loss for Real Image Denoising. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 729–735. https://doi.org/10.24963/ijcai.2021/101
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards