Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation
Abstract
Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body proportions. We introduce a verifier-guided augmentation framework that uses global and mode-local PCA to generate inexpensive candidates, screens them using correspondence-derived skeletal proportions and body-part geometry, and retrains a diffusion model on accepted candidates. Elastic registration provides both the modal structure used by distributed PCA and the dense anatomical correspondence needed for scalable screening without per-candidate body-model fitting. A blinded human study supports the verifier as a conservative gatekeeper, favoring verifier-accepted over rejected outputs. We evaluate full-pool verifier acceptance separately from the coverage and departure of accepted samples and combine them through EAUC. On 4,498 registered DFAUST surfaces, distributed-PCA augmentation achieves 86.32% acceptance, the highest CP-AUC (0.871), and the highest EAUC (0.752), improving EAUC by 32% over real-only and self-augmented diffusion. These results show that mode-local, verifier-guided proposals broaden diffusion generation while maintaining high agreement with calibrated body measurements.
Related
- Synthetic Data Augmentation for Functional Data: Wasserstein Risk Bounds and Diffusion-Based Conditional Generation
- Verifier-guided discovery of exact high-order mimetic operators with large language models
- Maximum Likelihood Estimation for Entity Ranking under Iterative Synthetic Data Augmentation
- DagFlow AI: Agentic Synthetic Data Generation for Personalized Statistics Learning
- An Energy-Driven Framework for Privacy-Aware Synthetic Data Generation
BibTeX
@misc{wu2026verifierguided,
title = {{Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation}},
author = {Yuexuan Wu and Yang Xiang and Hamid Laga and Dip Das and Anuj Srivastava and Zhengwu Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04006},
eprint = {2610.04006},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04006},
}
RIS
TY - UNPB
TI - Verifier-Guided Synthetic Augmentation for 3D Human Shape Generation
AU - Yuexuan Wu
AU - Yang Xiang
AU - Hamid Laga
AU - Dip Das
AU - Anuj Srivastava
AU - Zhengwu Zhang
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2610.04006
UR - https://arxiv.org/abs/2610.04006
AB - Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body proportions. We introduce a verifier-guided augmentation framework that uses global and mode-local PCA to generate inexpensive candidates, screens them using correspondence-derived skeletal proportions and body-part geometry, and retrains a diffusion model on accepted candidates. Elastic registration provides both the modal structure used by distributed PCA and the dense anatomical correspondence needed for scalable screening without per-candidate body-model fitting. A blinded human study supports the verifier as a conservative gatekeeper, favoring verifier-accepted over rejected outputs. We evaluate full-pool verifier acceptance separately from the coverage and departure of accepted samples and combine them through EAUC. On 4,498 registered DFAUST surfaces, distributed-PCA augmentation achieves 86.32% acceptance, the highest CP-AUC (0.871), and the highest EAUC (0.752), improving EAUC by 32% over real-only and self-augmented diffusion. These results show that mode-local, verifier-guided proposals broaden diffusion generation while maintaining high agreement with calibrated body measurements.
ER -