Xiao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiao Liu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chao Ren
Sichuan University
1 shared publication Dakun Yang
Sun Yat-sen University
1 shared publication- Jianhuang Lai
Sun Yat-Sen University, Guangzhou, China
1 shared publication - Jie Huang
College of Electronics and Information Engineering, Sichuan University, Chengdu, China
1 shared publication - Ling Mei
School of Electronic Information, Wuhan University of Science and Technology, Wuhan 430081, China
1 shared publication - Xiaohua Xie
Sun Yat-Sen University, Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12608-12618
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Deep learning methods have shown remarkable performance in image denoising, particularly when trained on large-scale paired datasets. However, acquiring such paired datasets for real-world scenarios poses a significant challenge. Although unsupervised approaches based on generative adversarial networks (GANs) offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers. To address this problem, we propose a self-collaboration (SC) strategy for multiple denoisers. This strategy can achieve significant performance improvement without increasing the inference complexity of the GAN-based denoising framework. Its basic idea is to iteratively replace the previous less powerful denoiser in the filter-guided noise extraction module with the current powerful denoiser. This process generates better synthetic clean-noisy image pairs, leading to a more powerful denoiser for the next iteration. In addition, we propose a baseline method that includes parallel generative adversarial branches with complementary "self-synthesis" and "unpaired-synthesis" constraints. This baseline ensures the stability and effectiveness of the training network. The experimental results demonstrate the superiority of our method over state-of-the-art unsupervised methods. https://github.com/linxin0/SCPGabNet
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12608-12618
Open AccessUnsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Deep learning methods have shown remarkable performance in image denoising, particularly when trained on large-scale paired datasets. However, acquiring such paired datasets for real-world scenarios poses a significant challenge. Although unsupervised approaches based on generative adversarial networks (GANs) offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers. To address this problem, we propose a self-collaboration (SC) strategy for multiple denoisers. This strategy can achieve significant performance improvement without increasing the inference complexity of the GAN-based denoising framework. Its basic idea is to iteratively replace the previous less powerful denoiser in the filter-guided noise extraction module with the current powerful denoiser. This process generates better synthetic clean-noisy image pairs, leading to a more powerful denoiser for the next iteration. In addition, we propose a baseline method that includes parallel generative adversarial branches with complementary "self-synthesis" and "unpaired-synthesis" constraints. This baseline ensures the stability and effectiveness of the training network. The experimental results demonstrate the superiority of our method over state-of-the-art unsupervised methods. https://github.com/linxin0/SCPGabNet
- 2 November 2018
- Published by Springer Nature
- p. 87-98
Feature Visualization Based Stacked Convolutional Neural Network for Human Body Detection in a Depth Image
- 2 November 2018
- Published by Springer Nature
- p. 87-98
Feature Visualization Based Stacked Convolutional Neural Network for Human Body Detection in a Depth Image