Search papers, labs, and topics across Lattice.
This paper investigates the impact of synthetic data augmentation on controllable human video generation using a diffusion-based framework that allows fine-grained control over appearance and motion. The study reveals the complementary roles of synthetic and real data in training, showing that synthetic data can enhance motion realism, temporal consistency, and identity preservation. The authors provide methods for efficiently selecting synthetic samples to improve the performance of generative models.
Synthetic data can significantly boost controllable human video generation, but only if you carefully select which synthetic samples to use.
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.
