# Learning Motion Refinement for Unsupervised Face Animation

arXiv: https://arxiv.org/abs/2310.13912 · HTML: https://mlsanity.com/paper/2310.13912/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 43 references that are in the map.
- First posted on arXiv 21 Oct 2023.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [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)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Animating Arbitrary Objects via Deep Motion Transfer](https://mlsanity.com/paper/1812.08861/) (2018)
- [X2Face: A network for controlling face generation by using images, audio, and pose codes](https://mlsanity.com/paper/1807.10550/) (2018)
- [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2203.06605/) (2022)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [GANimation: Anatomically-aware Facial Animation from a Single Image](https://mlsanity.com/paper/1807.09251/) (2018)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [Neural Head Reenactment with Latent Pose Descriptors](https://mlsanity.com/paper/2004.12000/) (2020)
- [HeadGAN: One-shot Neural Head Synthesis and Editing](https://mlsanity.com/paper/2012.08261/) (2020)
- [MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets](https://mlsanity.com/paper/1911.08139/) (2019)
- [3D Guided Fine-Grained Face Manipulation](https://mlsanity.com/paper/1902.08900/) (2019)
- [Implicit Warping for Animation with Image Sets](https://mlsanity.com/paper/2210.01794/) (2022)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [Py-Feat: Python Facial Expression Analysis Toolbox](https://mlsanity.com/paper/2104.03509/) (2021)

## Built on by (most cited first, 7 of 7)

- [HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation](https://mlsanity.com/paper/2503.18860/) (2025)
- [VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence](https://mlsanity.com/paper/2405.16204/) (2024)
- [Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation](https://mlsanity.com/paper/2412.00719/) (2024)
- [Free-viewpoint Human Animation with Pose-correlated Reference Selection](https://mlsanity.com/paper/2412.17290/) (2024)
- [One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing](https://mlsanity.com/paper/2412.06174/) (2024)
- [AI killed the video star. Audio-driven diffusion model for expressive talking head generation](https://mlsanity.com/paper/2511.22488/) (2025)
- [One-Shot Feed-Forward 360circ Animatable Avatar via Inpainted UV-Space Gaussian Modeling](https://mlsanity.com/paper/2601.12770/) (2026)

## Abstract (arXiv)

Unsupervised face animation aims to generate a human face video based on the appearance of a source image, mimicking the motion from a driving video. Existing methods typically adopted a prior-based motion model (e.g., the local affine motion model or the local thin-plate-spline motion model). While it is able to capture the coarse facial motion, artifacts can often be observed around the tiny motion in local areas (e.g., lips and eyes), due to the limited ability of these methods to model the finer facial motions. In this work, we design a new unsupervised face animation approach to learn simultaneously the coarse and finer motions. In particular, while exploiting the local affine motion model to learn the global coarse facial motion, we design a novel motion refinement module to compensate for the local affine motion model for modeling finer face motions in local areas. The motion refinement is learned from the dense correlation between the source and driving images. Specifically, we first construct a structure correlation volume based on the keypoint features of the source and driving images. Then, we train a model to generate the tiny facial motions iteratively from low to high resolution. The learned motion refinements are combined with the coarse motion to generate the new image. Extensive experiments on widely used benchmarks demonstrate that our method achieves the best results among state-of-the-art baselines.