# Differential Imaging Forensics

arXiv: https://arxiv.org/abs/1906.05268 · HTML: https://mlsanity.com/paper/1906.05268/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

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

- [Detecting Deepfake Videos Using Euler Video Magnification](https://mlsanity.com/paper/2101.11563/) (2021)

## Abstract (arXiv)

We introduce some new forensics based on differential imaging, where a novel category of visual evidence created via subtle interactions of light with a scene, such as dim reflections, can be computationally extracted and amplified from an image of interest through a comparative analysis with an additional reference baseline image acquired under similar conditions. This paradigm of differential imaging forensics (DIF) enables forensic examiners for the first time to retrieve the said visual evidence that is readily available in an image or video footage but would otherwise remain faint or even invisible to a human observer. We demonstrate the relevance and effectiveness of our approach through practical experiments. We also show that DIF provides a novel method for detecting forged images and video clips, including deep fakes.