# Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms

arXiv: https://arxiv.org/abs/2402.03188 · HTML: https://mlsanity.com/paper/2402.03188/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 87 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 36)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [Coupled Generative Adversarial Networks](https://mlsanity.com/paper/1606.07536/) (2016)
- [FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals](https://mlsanity.com/paper/1901.02212/) (2019)
- [DeepFaceLab: Integrated, flexible and extensible face-swapping framework](https://mlsanity.com/paper/2005.05535/) (2020)
- [Fast Face-swap Using Convolutional Neural Networks](https://mlsanity.com/paper/1611.09577/) (2016)
- [One Shot Face Swapping on Megapixels](https://mlsanity.com/paper/2105.04932/) (2021)
- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments](https://mlsanity.com/paper/2203.03339/) (2022)
- [Multi-style Generative Network for Real-time Transfer](https://mlsanity.com/paper/1703.06953/) (2017)
- [Natural and Effective Obfuscation by Head Inpainting](https://mlsanity.com/paper/1711.09001/) (2017)
- [Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds](https://mlsanity.com/paper/2105.06496/) (2021)
- [AnonymousNet: Natural Face De-Identification with Measurable Privacy](https://mlsanity.com/paper/1904.12620/) (2019)
- [Live Face De-Identification in Video](https://mlsanity.com/paper/1911.08348/) (2019)
- [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://mlsanity.com/paper/2110.11728/) (2021)
- [DeepFake Detection: Current Challenges and Next Steps](https://mlsanity.com/paper/2003.09234/) (2020)
- [Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation](https://mlsanity.com/paper/1908.00999/) (2019)
- [How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signals](https://mlsanity.com/paper/2008.11363/) (2020)

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

- [HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approach](https://mlsanity.com/paper/2609.27011/) (2026)

## Abstract (arXiv)

Advances in face swapping have enabled the automatic generation of highly realistic faces. Yet face swaps are perceived differently than when looking at real faces, with key differences in viewer behavior surrounding the eyes. Face swapping algorithms generally place no emphasis on the eyes, relying on pixel or feature matching losses that consider the entire face to guide the training process. We further investigate viewer perception of face swaps, focusing our analysis on the presence of an uncanny valley effect. We additionally propose a novel loss equation for the training of face swapping models, leveraging a pretrained gaze estimation network to directly improve representation of the eyes. We confirm that viewed face swaps do elicit uncanny responses from viewers. Our proposed improvements significant reduce viewing angle errors between face swaps and their source material. Our method additionally reduces the prevalence of the eyes as a deciding factor when viewers perform deepfake detection tasks. Our findings have implications on face swapping for special effects, as digital avatars, as privacy mechanisms, and more; negative responses from users could limit effectiveness in said applications. Our gaze improvements are a first step towards alleviating negative viewer perceptions via a targeted approach.