Zero-Shot Image Denoising for High-Resolution Electron Microscopy
This addresses denoising for material imaging researchers, offering an incremental improvement by integrating existing techniques like super-resolution and random sub-sampling into a zero-shot framework.
The paper tackles denoising in high-resolution electron microscopy (HREM) images, which suffer from ultra-low signal-to-noise ratio and scarce data, by proposing Noise2SR, a zero-shot self-supervised learning framework that uses a super-resolution-based training strategy and random sub-sampling to generate noisy pairs from a single image. It outperforms state-of-the-art zero-shot methods and achieves comparable performance to supervised methods in simulated and real HREM tasks.
High-resolution electron microscopy (HREM) imaging technique is a powerful tool for directly visualizing a broad range of materials in real-space. However, it faces challenges in denoising due to ultra-low signal-to-noise ratio (SNR) and scarce data availability. In this work, we propose Noise2SR, a zero-shot self-supervised learning (ZS-SSL) denoising framework for HREM. Within our framework, we propose a super-resolution (SR) based self-supervised training strategy, incorporating the Random Sub-sampler module. The Random Sub-sampler is designed to generate approximate infinite noisy pairs from a single noisy image, serving as an effective data augmentation in zero-shot denoising. Noise2SR trains the network with paired noisy images of different resolutions, which is conducted via SR strategy. The SR-based training facilitates the network adopting more pixels for supervision, and the random sub-sampling helps compel the network to learn continuous signals enhancing the robustness. Meanwhile, we mitigate the uncertainty caused by random-sampling by adopting minimum mean squared error (MMSE) estimation for the denoised results. With the distinctive integration of training strategy and proposed designs, Noise2SR can achieve superior denoising performance using a single noisy HREM image. We evaluate the performance of Noise2SR in both simulated and real HREM denoising tasks. It outperforms state-of-the-art ZS-SSL methods and achieves comparable denoising performance with supervised methods. The success of Noise2SR suggests its potential for improving the SNR of images in material imaging domains.