Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edits temporally, strictly preserving background invariance while enabling plausible, text-driven interactions between the inserted object and the dynamic environment. Our approach hinges on non-invasive guidance mechanisms that enforce structural consistency, facilitate seamless boundary fusion, and counteract the fidelity drift that typically accumulates during the denoising trajectory. Extensive quantitative experiments validate our efficacy: SimInsert surpasses state-of-the-art methods with an 18.8\% gain in PSNR, 20.1\% in SSIM, and a 44.1\% decrease in LPIPS, offering a streamlined solution for high-fidelity video editing.
@article{arxiv.2605.23245,
title = {SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion},
author = {Xinyu Chen and Yuyi Qian and Jiang Lin and Shenyi Wang and Gao Wang and Zhiqiu Zhang and Jizhi Zhang and Mingjie Wang and Qiang Tang and Qian Wang and Song Wu and Zili Yi},
journal= {arXiv preprint arXiv:2605.23245},
year = {2026}
}