# Machine learning method for light field refocusing

arXiv: https://arxiv.org/abs/2103.16020 · HTML: https://mlsanity.com/paper/2103.16020/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Learning to Synthesize a 4D RGBD Light Field from a Single Image](https://mlsanity.com/paper/1708.03292/) (2017)
- [Aperture Supervision for Monocular Depth Estimation](https://mlsanity.com/paper/1711.07933/) (2017)
- [Light Field Compression by Residual CNN Assisted JPEG](https://mlsanity.com/paper/2010.00062/) (2020)

## Built on by (most cited first, 1 of 1)

- [Arbitrary Volumetric Refocusing of Dense and Sparse Light Fields](https://mlsanity.com/paper/2502.19238/) (2025)

## Abstract (arXiv)

Light field imaging introduced the capability to refocus an image after capturing. Currently there are two popular methods for refocusing, shift-and-sum and Fourier slice methods. Neither of these two methods can refocus the light field in real-time without any pre-processing. In this paper we introduce a machine learning based refocusing technique that is capable of extracting 16 refocused images with refocusing parameters of α=0.125,0.250,0.375,...,2.0 in real-time. We have trained our network, which is called RefNet, in two experiments. Once using the Fourier slice method as the training -- i.e., "ground truth" -- data and another using the shift-and-sum method as the training data. We showed that in both cases, not only is the RefNet method at least 134x faster than previous approaches, but also the color prediction of RefNet is superior to both Fourier slice and shift-and-sum methods while having similar depth of field and focus distance performance.