# X2C: A Large-Scale Benchmark for Nuanced Humanoid Facial Expression Imitation

arXiv: https://arxiv.org/abs/2505.11146 · HTML: https://mlsanity.com/paper/2505.11146/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 104 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [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)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (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)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024)
- [Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis](https://mlsanity.com/paper/1909.12224/) (2019)
- [GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis](https://mlsanity.com/paper/2301.13430/) (2023)

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

- [SingingBot: An Avatar-Driven System for Robotic Face Singing Performance](https://mlsanity.com/paper/2601.02125/) (2026)

## Abstract (arXiv)

Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces. While visual synthesis of talking heads has advanced rapidly, mapping high-dimensional visual cues to precise, physically constrained actuation signals remains an open problem, primarily due to the lack of large-scale paired data. To bridge this gap, we introduce X2C, a comprehensive benchmark dataset comprising 100,000 (image, control value) pairs. Unlike existing resources, X2C features nuanced, physically grounded expressions annotated with 30 continuous control parameters, establishing a high-fidelity standard for this task. Building on this resource, we propose X2CNet, a two-stage deep learning framework that explicitly decouples visual motion features from mechanical control regression to model the correspondence between human perceptual cues and humanoid actuation. Extensive experiments, including quantitative benchmarking and real-world physical validation, demonstrate that our approach achieves superior cross-domain consistency and enables robust, in-the-wild expression imitation. Code and Data: https://lipzh5.github.io/X2CNet/