mlsanityData to 7 Oct 2026

ExFace: Expressive Facial Control for Humanoid Robots with Diffusion Transformers and Bootstrap Training

arXiv 2504.14477 ↗First posted 20 Apr 2025cs.ROcited by 1

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

This paper presents a novel Expressive Facial Control (ExFace) method based on Diffusion Transformers, which achieves precise mapping from human facial blendshapes to bionic robot motor control. By incorporating an innovative model bootstrap training strategy, our approach not only generates high-quality facial expressions but also significantly improves accuracy and smoothness. Experimental results demonstrate that the proposed method outperforms previous methods in terms of accuracy, frame per second (FPS), and response time. Furthermore, we develop the ExFace dataset driven by human facial data. ExFace shows excellent real-time performance and natural expression rendering in applications such as robot performances and human-robot interactions, offering a new solution for bionic robot interaction.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 11 of its 24 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

11 of 24 references.

References · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  8. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  9. 2023Diffusion Models for Reinforcement Learning: A Surveycited by 84
  10. 2024Media2Face: Co-speech Facial Animation Generation With Multi-Modality Guidancecited by 39
  11. 2021Smile Like You Mean It: Driving Animatronic Robotic Face with Learned Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SingingBot: An Avatar-Driven System for Robotic Face Singing Performancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Expressive Whole-Body Control for Humanoid Robots
  2. 2026Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots ↗
  3. 2025FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction
  4. 2025Generation of Real-time Robotic Emotional Expressions Learning from Human Demonstration in Mixed Reality ↗
  5. 2025FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
  6. 2025DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance
  7. 2025Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models
  8. 2025Controllable Expressive 3D Facial Animation via Diffusion in a Unified Multimodal Space