# Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space

arXiv: https://arxiv.org/abs/2307.15461 · HTML: https://mlsanity.com/paper/2307.15461/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [Gaussian Kernel Mixture Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2111.00454/) (2021)
- [Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions](https://mlsanity.com/paper/1807.06650/) (2018)
- [Single-shot autofocusing of microscopy images using deep learning](https://mlsanity.com/paper/2003.09585/) (2020)
- [Blind deblurring for microscopic pathology images using deep learning networks](https://mlsanity.com/paper/2011.11879/) (2020)
- [Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections](https://mlsanity.com/paper/1603.09056/) (2016)
- [BaMBNet: A Blur-aware Multi-branch Network for Defocus Deblurring](https://mlsanity.com/paper/2105.14766/) (2021)

## Abstract (arXiv)

Though modern microscopes have an autofocusing system to ensure optimal focus, out-of-focus images can still occur when cells within the medium are not all in the same focal plane, affecting the image quality for medical diagnosis and analysis of diseases. We propose a method that can deblur images as well as synthesize defocus blur. We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations among the representations of different blur levels in the latent space. This allows for the exploration of different blur levels of an object by linearly interpolating/extrapolating the latent representations of images taken at different focal planes. Compared to existing works, we use a simple architecture to synthesize images with flexible blur levels, leveraging the linear latent space. Our regularized autoencoders can effectively mimic blur and deblur, increasing data variety as a data augmentation technique and improving the quality of microscopic images, which would be beneficial for further processing and analysis.