Shi Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shi Zhao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Lei Zhu
Peking University
2 shared publications - Lujia Jin
Peking University
2 shared publications - Qian Chen
Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China
2 shared publications - Yanye Lu
Peking University
2 shared publications - Qing Guo
Chinese Academy of Cultural Heritage, Beijing, China
1 shared publication - Qiushi Ren
Department of Biomedical Engineering, College of Future Technology, Peking University, Beijing, China
1 shared publication
Latest Publications
- 9 September 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (2) , 515-536
One-Pot Multi-frame Denoising
- 9 September 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (2) , 515-536
One-Pot Multi-frame Denoising
- Open Access
One-Pot Multi-Frame Denoising
The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional supervision schemes including both supervised Noise2Clean (N2C) and unsupervised Noise2Noise (N2N), OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision and allows models to mine deeper into the correlation among frames. N2N has also been proved to be actually a simplified case of the proposed OPD. From the perspectives of data allocation and loss function, two specific implementations, random coupling (RC) and alienation loss (AL), are respectively provided to accomplish OPD during model training. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method and is comparable to supervised N2C methods for synthetic Gaussian and Poisson noise, and real-world optical coherence tomography (OCT) speckle noise.
Open AccessOne-Pot Multi-Frame Denoising
The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional supervision schemes including both supervised Noise2Clean (N2C) and unsupervised Noise2Noise (N2N), OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision and allows models to mine deeper into the correlation among frames. N2N has also been proved to be actually a simplified case of the proposed OPD. From the perspectives of data allocation and loss function, two specific implementations, random coupling (RC) and alienation loss (AL), are respectively provided to accomplish OPD during model training. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method and is comparable to supervised N2C methods for synthetic Gaussian and Poisson noise, and real-world optical coherence tomography (OCT) speckle noise.