# LI-Net: Large-Pose Identity-Preserving Face Reenactment Network

arXiv: https://arxiv.org/abs/2104.02850 · HTML: https://mlsanity.com/paper/2104.02850/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [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)
- [X2Face: A network for controlling face generation by using images, audio, and pose codes](https://mlsanity.com/paper/1807.10550/) (2018)
- [ReenactGAN: Learning to Reenact Faces via Boundary Transfer](https://mlsanity.com/paper/1807.11079/) (2018)

## Built on by (most cited first, 9 of 9)

- [Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis](https://mlsanity.com/paper/2211.14506/) (2022)
- [OPT: One-shot Pose-Controllable Talking Head Generation](https://mlsanity.com/paper/2302.08197/) (2023)
- [OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions](https://mlsanity.com/paper/2309.16148/) (2023)
- [Emotional Conversation: Empowering Talking Faces with Cohesive Expression, Gaze and Pose Generation](https://mlsanity.com/paper/2406.07895/) (2024)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [MaskRenderer: 3D-Infused Multi-Mask Realistic Face Reenactment](https://mlsanity.com/paper/2309.05095/) (2023)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [Learning Semantic Facial Descriptors for Accurate Face Animation](https://mlsanity.com/paper/2501.17718/) (2025)
- [LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space](https://mlsanity.com/paper/2411.09268/) (2024)

## Abstract (arXiv)

Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously. Most existing methods directly apply driving facial landmarks to reenact source faces and ignore the intrinsic gap between two identities, resulting in the identity mismatch issue. Besides, they neglect the entanglement of expression and pose features when encoding driving faces, leading to inaccurate expressions and visual artifacts on large-pose reenacted faces. To address these problems, we propose a Large-pose Identity-preserving face reenactment network, LI-Net. Specifically, the Landmark Transformer is adopted to adjust driving landmark images, which aims to narrow the identity gap between driving and source landmark images. Then the Face Rotation Module and the Expression Enhancing Generator decouple the transformed landmark image into pose and expression features, and reenact those attributes separately to generate identity-preserving faces with accurate expressions and poses. Both qualitative and quantitative experimental results demonstrate the superiority of our method.