Compositing human figures into scene images has broad applications in areas such as entertainment and advertising. However, existing methods often cannot handle occlusion of the inserted person by foreground objects and unnaturally place the person in the frontmost layer. Moreover, they offer limited control over the inserted person's pose. To address these challenges, we propose two methods. Both allow explicit pose control via a 3D body model and leverage latent diffusion models to synthesize the person at a contextually appropriate depth, naturally handling occlusions without requiring occlusion masks. The first is a two-stage approach: the model first learns a depth map of the scene with the person through supervised learning, and then synthesizes the person accordingly. The second method learns occlusion implicitly and synthesizes the person directly from input data without explicit depth supervision. Quantitative and qualitative evaluations show that both methods outperform existing approaches by better preserving scene consistency while accurately reflecting occlusions and user-specified poses.
@article{shun2025personinsitu,
title={{Person-In-Situ: Scene-Consistent Human Image Insertion with Occlusion-Aware Pose Control}},
author={Shun Masuda and Yuki Endo and Yoshihiro Kanamori},
journal={arXiv:2505.04052},
year={2025}
}