# Semi- and Self-Supervised Multi-View Fusion of 3D Microscopy Images using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2108.02743 · HTML: https://mlsanity.com/paper/2108.02743/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 5 Aug 2021.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Learning to Deblur](https://mlsanity.com/paper/1406.7444/) (2014)
- [Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution](https://mlsanity.com/paper/1611.06495/) (2016)
- [CycleGAN with a Blur Kernel for Deconvolution Microscopy: Optimal Transport Geometry](https://mlsanity.com/paper/1908.09414/) (2019)
- [Improving Blind Spot Denoising for Microscopy](https://mlsanity.com/paper/2008.08414/) (2020)
- [DeepDeblur: Fast one-step blurry face images restoration](https://mlsanity.com/paper/1711.09515/) (2017)
- [Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer](https://mlsanity.com/paper/1904.02910/) (2019)

## Built on by (most cited first, 2 of 2)

- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [Biomedical Image Reconstruction: A Survey](https://mlsanity.com/paper/2301.11813/) (2023)

## Abstract (arXiv)

Recent developments in fluorescence microscopy allow capturing high-resolution 3D images over time for living model organisms. To be able to image even large specimens, techniques like multi-view light-sheet imaging record different orientations at each time point that can then be fused into a single high-quality volume. Based on measured point spread functions (PSF), deconvolution and content fusion are able to largely revert the inevitable degradation occurring during the imaging process. Classical multi-view deconvolution and fusion methods mainly use iterative procedures and content-based averaging. Lately, Convolutional Neural Networks (CNNs) have been deployed to approach 3D single-view deconvolution microscopy, but the multi-view case waits to be studied. We investigated the efficacy of CNN-based multi-view deconvolution and fusion with two synthetic data sets that mimic developing embryos and involve either two or four complementary 3D views. Compared with classical state-of-the-art methods, the proposed semi- and self-supervised models achieve competitive and superior deconvolution and fusion quality in the two-view and quad-view cases, respectively.