PainDiffusion: Learning to Express Pain

TL;DR

PainDiffusion is a novel generative model that synthesizes realistic facial pain expressions for clinical training and human-robot interaction, offering personalized, smooth, and controllable pain expression synthesis in real-time.

Contribution

It introduces a diffusion-based generative approach for naturalistic pain expression synthesis, improving realism and controllability over existing methods.

Findings

Produces realistic pain expressions with 31.2% preference over ground truth.

Supports indefinite-length, smooth facial motion in pain expression synthesis.

Effective integration into robotic systems for real-time rehabilitation exercises.

Abstract

Accurate pain expression synthesis is essential for improving clinical training and human-robot interaction. Current Robotic Patient Simulators (RPSs) lack realistic pain facial expressions, limiting their effectiveness in medical training. In this work, we introduce PainDiffusion, a generative model that synthesizes naturalistic facial pain expressions. Unlike traditional heuristic or autoregressive methods, PainDiffusion operates in a continuous latent space, ensuring smoother and more natural facial motion while supporting indefinite-length generation via diffusion forcing. Our approach incorporates intrinsic characteristics such as pain expressiveness and emotion, allowing for personalized and controllable pain expression synthesis. We train and evaluate our model using the BioVid HeatPain Database. Additionally, we integrate PainDiffusion into a robotic system to assess its applicability in real-time rehabilitation exercises. Qualitative studies with clinicians reveal that PainDiffusion produces realistic pain expressions, with a 31.2% (std 4.8%) preference rate against ground-truth recordings. Our results suggest that PainDiffusion can serve as a viable alternative to real patients in clinical training and simulation, bridging the gap between synthetic and naturalistic pain expression. Code and videos are available at: https://damtien444.github.io/paindf/