Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation

TL;DR

This paper systematically investigates how synthetic data can enhance controllable human video generation, revealing their complementary roles and proposing methods to improve realism and consistency.

Contribution

It introduces a diffusion-based framework for analyzing synthetic data's impact on human video synthesis, providing practical insights for data-efficient model training.

Findings

Synthetic data complements real data in improving motion realism.

Methods for selecting synthetic samples enhance temporal consistency.

The framework enables fine-grained control over appearance and motion.

Abstract

Controllable human video generation aims to produce realistic videos of humans with explicitly guided motions and appearances,serving as a foundation for digital humans, animation, and embodied AI.However, the scarcity of largescale, diverse, and privacy safe human video datasets poses a major bottleneck, especially for rare identities and complex actions.Synthetic data provides a scalable and controllable alternative,yet its actual contribution to generative modeling remains underexplored due to the persistent Sim2Real gap.In this work,we systematically investigate the impact of synthetic data on controllable human video generation. We propose a diffusion-based framework that enables fine-grained control over appearance and motion while providing a unfied testbed to analyze how synthetic data interacts with real world data during training. Through extensive experiments, we reveal the complementary roles of synthetic and real data and demonstrate possible methods for efficiently selecting synthetic samples to enhance motion realism,temporal consistency,and identity preservation.Our study offers the first comprehensive exploration of synthetic data's role in human-centric video synthesis and provides practical insights for building data-efficient and generalizable generative models.