Clean Implicit 3D Structure from Noisy 2D STEM Images
This work addresses the challenge of 3D reconstruction in microscopy for researchers, but it is incremental as it builds on existing implicit representation and noise modeling techniques.
The paper tackled the problem of reconstructing 3D structures from noisy 2D STEM images by proposing a differentiable image formation model that jointly learns sensor noise and an implicit 3D model, achieving unsupervised disentanglement of signal and noise and outperforming baselines on synthetic and real data.
Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components. Unfortunately, these 2D images can be too noisy to be fused into a useful 3D structure and facilitating good denoisers is challenging due to the lack of clean-noisy pairs. Additionally, representing a detailed 3D structure can be difficult even for clean data when using regular 3D grids. Addressing these two limitations, we suggest a differentiable image formation model for STEM, allowing to learn a joint model of 2D sensor noise in STEM together with an implicit 3D model. We show, that the combination of these models are able to successfully disentangle 3D signal and noise without supervision and outperform at the same time several baselines on synthetic and real data.