# Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment

arXiv: https://arxiv.org/abs/2509.16727 · HTML: https://mlsanity.com/paper/2509.16727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN](https://mlsanity.com/paper/2203.04036/) (2022)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [DiffusionNet: Discretization Agnostic Learning on Surfaces](https://mlsanity.com/paper/2012.00888/) (2020)
- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation](https://mlsanity.com/paper/2411.02293/) (2024)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild](https://mlsanity.com/paper/2305.08296/) (2023)
- [Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond](https://mlsanity.com/paper/2403.10667/) (2024)
- [MagicFace: High-Fidelity Facial Expression Editing with Action-Unit Control](https://mlsanity.com/paper/2501.02260/) (2025)
- [Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training](https://mlsanity.com/paper/2101.03251/) (2021)
- [SynPAIN: A Synthetic Dataset of Pain and Non-Pain Facial Expressions](https://mlsanity.com/paper/2507.19673/) (2025)
- [Fully-attentive and interpretable: vision and video vision transformers for pain detection](https://mlsanity.com/paper/2210.15769/) (2022)
- [Conditional Adversarial Synthesis of 3D Facial Action Units](https://mlsanity.com/paper/1802.07421/) (2018)

## Abstract (arXiv)

Automated pain assessment from facial expressions is crucial for non-communicative patient. Progress has been limited by two challenges: (i) existing datasets exhibit severe demographic and label imbalance due to ethical constraints, and (ii) current generative models cannot precisely control facial action units (AUs), facial structure, or clinically validated pain levels. We introduce 3DPain, a large-scale synthetic dataset designed to overcome data scarcity in automated pain assessment. Comprising 82,500 frames across 2,500 unique identities, 3DPain offers extensive heterogeneity in facial pain responses across demographic groups balanced by age, gender, and ethnicity. Our three-stage framework samples diverse 3D meshes, textures them with diffusion models, and applies AU-driven face rigging to synthesize multi-view faces with paired neutral/pain images, facial action units, PSPI scores, and pain-region heatmaps. We further introduce ViTPain, a Vision Transformer based framework leveraging cross-attention with a neutral reference face to achieve identityaware pain estimation. Together, 3DPain and ViTPain establish a controllable, diverse, and clinically grounded foundation for generalizable automated pain assessment.