# SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion

arXiv: https://arxiv.org/abs/2605.23245 · HTML: https://mlsanity.com/paper/2605.23245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 23 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 23 of 23)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [Video-P2P: Video Editing with Cross-attention Control](https://mlsanity.com/paper/2303.04761/) (2023)
- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://mlsanity.com/paper/2312.04433/) (2023)
- [AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks](https://mlsanity.com/paper/2403.14468/) (2024)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [ReVideo: Remake a Video with Motion and Content Control](https://mlsanity.com/paper/2405.13865/) (2024)
- [VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence](https://mlsanity.com/paper/2312.02087/) (2023)
- [I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models](https://mlsanity.com/paper/2405.16537/) (2024)
- [MiniMax-Remover: Taming Bad Noise Helps Video Object Removal](https://mlsanity.com/paper/2505.24873/) (2025)
- [VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control](https://mlsanity.com/paper/2501.01427/) (2025)
- [Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.07132/) (2024)
- [ObjectMover: Generative Object Movement with Video Prior](https://mlsanity.com/paper/2503.08037/) (2025)
- [MVOC: a training-free multiple video object composition method with diffusion models](https://mlsanity.com/paper/2406.15829/) (2024)
- [Re-Attentional Controllable Video Diffusion Editing](https://mlsanity.com/paper/2412.11710/) (2024)

## Abstract (arXiv)

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 textitSimInsert, 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.