SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913154912485376 |
|---|---|
| author | Chen, Xinyu Qian, Yuyi Lin, Jiang Wang, Shenyi Wang, Gao Zhang, Zhiqiu Zhang, Jizhi Wang, Mingjie Tang, Qiang Wang, Qian Wu, Song Yi, Zili |
| author_facet | Chen, Xinyu Qian, Yuyi Lin, Jiang Wang, Shenyi Wang, Gao Zhang, Zhiqiu Zhang, Jizhi Wang, Mingjie Tang, Qiang Wang, Qian Wu, Song Yi, Zili |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23245 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion Chen, Xinyu Qian, Yuyi Lin, Jiang Wang, Shenyi Wang, Gao Zhang, Zhiqiu Zhang, Jizhi Wang, Mingjie Tang, Qiang Wang, Qian Wu, Song Yi, Zili Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.23245 |