# On Face Segmentation, Face Swapping, and Face Perception

arXiv: https://arxiv.org/abs/1704.06729 · HTML: https://mlsanity.com/paper/1704.06729/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2017.

## Built on by (most cited first, 30 of 71)

- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [Protecting Celebrities from DeepFake with Identity Consistency Transformer](https://mlsanity.com/paper/2203.01318/) (2022)
- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [BlendFace: Re-designing Identity Encoders for Face-Swapping](https://mlsanity.com/paper/2307.10854/) (2023)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [High-resolution Face Swapping via Latent Semantics Disentanglement](https://mlsanity.com/paper/2203.15958/) (2022)
- [LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar](https://mlsanity.com/paper/2305.01190/) (2023)
- [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022)
- [FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping](https://mlsanity.com/paper/2210.10473/) (2022)
- [MobileFaceSwap: A Lightweight Framework for Video Face Swapping](https://mlsanity.com/paper/2201.03808/) (2022)
- [StyleSwap: Style-Based Generator Empowers Robust Face Swapping](https://mlsanity.com/paper/2209.13514/) (2022)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/2202.12972/) (2022)
- [Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness](https://mlsanity.com/paper/2112.05907/) (2021)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Few-Shot Head Swapping in the Wild](https://mlsanity.com/paper/2204.13100/) (2022)
- [Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics](https://mlsanity.com/paper/2507.18015/) (2025)
- [G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors](https://mlsanity.com/paper/2408.09458/) (2024)
- [The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimation](https://mlsanity.com/paper/2109.10471/) (2021)
- [AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing](https://mlsanity.com/paper/2101.07034/) (2021)
- [CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation](https://mlsanity.com/paper/2507.02691/) (2025)
- [A Study of the Human Perception of Synthetic Faces](https://mlsanity.com/paper/2111.04230/) (2021)
- [My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymization](https://mlsanity.com/paper/2211.01361/) (2022)
- [Learning Disentangled Representation for One-shot Progressive Face Swapping](https://mlsanity.com/paper/2203.12985/) (2022)
- [FIVA: Facial Image and Video Anonymization and Anonymization Defense](https://mlsanity.com/paper/2309.04228/) (2023)
- [UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing](https://mlsanity.com/paper/2108.05650/) (2021)

## Abstract (arXiv)

We show that even when face images are unconstrained and arbitrarily paired, face swapping between them is actually quite simple. To this end, we make the following contributions. (a) Instead of tailoring systems for face segmentation, as others previously proposed, we show that a standard fully convolutional network (FCN) can achieve remarkably fast and accurate segmentations, provided that it is trained on a rich enough example set. For this purpose, we describe novel data collection and generation routines which provide challenging segmented face examples. (b) We use our segmentations to enable robust face swapping under unprecedented conditions. (c) Unlike previous work, our swapping is robust enough to allow for extensive quantitative tests. To this end, we use the Labeled Faces in the Wild (LFW) benchmark and measure the effect of intra- and inter-subject face swapping on recognition. We show that our intra-subject swapped faces remain as recognizable as their sources, testifying to the effectiveness of our method. In line with well known perceptual studies, we show that better face swapping produces less recognizable inter-subject results. This is the first time this effect was quantitatively demonstrated for machine vision systems.