# Totems: Physical Objects for Verifying Visual Integrity

arXiv: https://arxiv.org/abs/2209.13032 · HTML: https://mlsanity.com/paper/2209.13032/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 23 of 23)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Exposing Deep Fakes Using Inconsistent Head Poses](https://mlsanity.com/paper/1811.00661/) (2018)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [The Deepfake Detection Challenge (DFDC) Preview Dataset](https://mlsanity.com/paper/1910.08854/) (2019)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [Learning Self-Consistency for Deepfake Detection](https://mlsanity.com/paper/2012.09311/) (2020)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [Two-Stream Neural Networks for Tampered Face Detection](https://mlsanity.com/paper/1803.11276/) (2018)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Detecting Photoshopped Faces by Scripting Photoshop](https://mlsanity.com/paper/1906.05856/) (2019)
- [Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes](https://mlsanity.com/paper/2004.10904/) (2020)
- [Seeing the World in a Bag of Chips](https://mlsanity.com/paper/2001.04642/) (2020)
- [Exposing Fake Images with Forensic Similarity Graphs](https://mlsanity.com/paper/1912.02861/) (2019)
- [Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization](https://mlsanity.com/paper/1912.02314/) (2019)
- [What You Can Learn by Staring at a Blank Wall](https://mlsanity.com/paper/2108.13027/) (2021)
- [Sparkle Vision: Seeing the World through Random Specular Microfacets](https://mlsanity.com/paper/1412.7884/) (2014)

## Built on by (most cited first, 3 of 3)

- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [Principles of Designing Robust Remote Face Anti-Spoofing Systems](https://mlsanity.com/paper/2406.03684/) (2024)
- [Noise-Coded Illumination for Forensic and Photometric Video Analysis](https://mlsanity.com/paper/2507.23002/) (2025)

## Abstract (arXiv)

We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems bend and redirect light rays, thus providing multiple, albeit distorted, views of the scene within a single image. A defender can use these distorted totem pixels to detect if an image has been manipulated. Our approach unscrambles the light rays passing through the totems by estimating their positions in the scene and using their known geometric and material properties. To verify a totem-protected image, we detect inconsistencies between the scene reconstructed from totem viewpoints and the scene's appearance from the camera viewpoint. Such an approach makes the adversarial manipulation task more difficult, as the adversary must modify both the totem and image pixels in a geometrically consistent manner without knowing the physical properties of the totem. Unlike prior learning-based approaches, our method does not require training on datasets of specific manipulations, and instead uses physical properties of the scene and camera to solve the forensics problem.