Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution
Ruian He, Ri Cheng, Xinkai Lyu, Weimin Tan, Bo Yan
Abstract
In time-lapse microscopy, inherent noise significantly limits imaging sensitivity and increases measurement uncertainty. Due to the scarcity of clean data, zero-shot approaches have emerged as highly data-efficient solutions for microscopy denoising. However, existing methods typically process video frames independently, resulting in long training times and issues such as temporal noise and over-smoothing. In this paper, we introduce MDSR-Zero, a zero-shot online learning method designed for plug-and-play noise suppression and super-resolution of microscopy videos. Our approach leverages an efficient online training strategy that reuses denoising models from previous frames. By treating the video as a continuous stream, our model significantly reduces training time and ensures temporally consistent denoising. Additionally, we propose a novel loss function tailored for denoising in the context of super-resolution, which enhances the detail in the denoised results. Extensive experiments on both synthetic and real-world noise demonstrate that our method achieves state-of-the-art performance among zero-shot denoising approaches and is competitive with self-supervised methods. Notably, our method can reduce training time by up to 10x compared to the previous SOTA method.
BibTeX
@article{He_Cheng_Lyu_Tan_Yan_2025, title={Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32354}, DOI={10.1609/aaai.v39i3.32354}, abstractNote={In time-lapse microscopy, inherent noise significantly limits imaging sensitivity and increases measurement uncertainty. Due to the scarcity of clean data, zero-shot approaches have emerged as highly data-efficient solutions for microscopy denoising. However, existing methods typically process video frames independently, resulting in long training times and issues such as temporal noise and over-smoothing. In this paper, we introduce MDSR-Zero, a zero-shot online learning method designed for plug-and-play noise suppression and super-resolution of microscopy videos. Our approach leverages an efficient online training strategy that reuses denoising models from previous frames. By treating the video as a continuous stream, our model significantly reduces training time and ensures temporally consistent denoising. Additionally, we propose a novel loss function tailored for denoising in the context of super-resolution, which enhances the detail in the denoised results. Extensive experiments on both synthetic and real-world noise demonstrate that our method achieves state-of-the-art performance among zero-shot denoising approaches and is competitive with self-supervised methods. Notably, our method can reduce training time by up to 10x compared to the previous SOTA method.}, number={3}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={He, Ruian and Cheng, Ri and Lyu, Xinkai and Tan, Weimin and Yan, Bo}, year={2025}, month={Apr.}, pages={3419-3427} }