# InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

arXiv: https://arxiv.org/abs/2512.17504 · HTML: https://mlsanity.com/paper/2512.17504/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 26 of its 28 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler](https://mlsanity.com/paper/2502.20110/) (2025)
- [AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks](https://mlsanity.com/paper/2403.14468/) (2024)
- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [ReVideo: Remake a Video with Motion and Content Control](https://mlsanity.com/paper/2405.13865/) (2024)
- [Se~norita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists](https://mlsanity.com/paper/2502.06734/) (2025)
- [VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control](https://mlsanity.com/paper/2501.01427/) (2025)
- [OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting](https://mlsanity.com/paper/2503.08677/) (2025)
- [ROSE: Remove Objects with Side Effects in Videos](https://mlsanity.com/paper/2508.18633/) (2025)
- [Generative Video Propagation](https://mlsanity.com/paper/2412.19761/) (2024)
- [Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video](https://mlsanity.com/paper/2503.21761/) (2025)
- [InVi: Object Insertion In Videos Using Off-the-Shelf Diffusion Models](https://mlsanity.com/paper/2407.10958/) (2024)
- [Anything in Any Scene: Photorealistic Video Object Insertion](https://mlsanity.com/paper/2401.17509/) (2024)
- [OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models](https://mlsanity.com/paper/2509.17627/) (2025)
- [DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Image](https://mlsanity.com/paper/2503.10342/) (2025)

## Abstract (arXiv)

Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections. To address these limitations, we present InsertAnywhere, a comprehensive VOI framework that achieves geometrically grounded object placement and optics-aware video synthesis. Our approach first leverages a 4D-aware mask generation module that allows users to anchor an object's 3D pose in a single frame. The framework automatically propagates this placement across the video, accurately handling local scene dynamics and occlusions. To synthesize realistic physical lighting interactions, we introduce Optics-Aware Representation Alignment, a novel strategy that utilizes an extended mask to guide feature extraction, enabling optical effects to seamlessly extend beyond the inserted object's boundary. Finally, to overcome the lack of training data for such phenomena, we construct and open-source ROSE++, a specialized quadruplet dataset tailored for the supervised learning of optical effects. Extensive experiments demonstrate that InsertAnywhere produces geometrically plausible and photometrically realistic insertions in complex real-world scenarios, significantly outperforming existing research and commercial generative tools.