# FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors

arXiv: https://arxiv.org/abs/2505.01322 · HTML: https://mlsanity.com/paper/2505.01322/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 24 of 24)

- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023)
- [DreamEditor: Text-Driven 3D Scene Editing with Neural Fields](https://mlsanity.com/paper/2306.13455/) (2023)
- [GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing](https://mlsanity.com/paper/2403.08733/) (2024)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts](https://mlsanity.com/paper/2401.14828/) (2024)
- [FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly](https://mlsanity.com/paper/2308.10608/) (2023)
- [ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields](https://mlsanity.com/paper/2402.00864/) (2024)
- [Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects](https://mlsanity.com/paper/2412.00518/) (2024)
- [MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing](https://mlsanity.com/paper/2408.08000/) (2024)
- [SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation](https://mlsanity.com/paper/2412.01801/) (2024)
- [Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint](https://mlsanity.com/paper/2410.15391/) (2024)
- [ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF](https://mlsanity.com/paper/2310.02712/) (2023)
- [T2TD: Text-3D Generation Model based on Prior Knowledge Guidance](https://mlsanity.com/paper/2305.15753/) (2023)
- [InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes](https://mlsanity.com/paper/2401.05335/) (2024)
- [Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates](https://mlsanity.com/paper/2309.11281/) (2023)
- [UVMap-ID: A Controllable and Personalized UV Map Generative Model](https://mlsanity.com/paper/2404.14568/) (2024)
- [GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization](https://mlsanity.com/paper/2411.10033/) (2024)
- [Point Cloud Completion Guided by Prior Knowledge via Causal Inference](https://mlsanity.com/paper/2305.17770/) (2023)

## Built on by (most cited first, 5 of 5)

- [TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking](https://mlsanity.com/paper/2604.01207/) (2026)
- [PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems](https://mlsanity.com/paper/2604.16540/) (2026)
- [HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placement](https://mlsanity.com/paper/2604.10675/) (2026)
- [Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.12183/) (2026)
- [Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems](https://mlsanity.com/paper/2604.25544/) (2026)

## Abstract (arXiv)

Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and they struggle to ensure consistency of the inserted object. These limitations hinder flexibility and scalability in real-world applications. In this paper, we propose FreeInsert, a novel framework that leverages foundation models including MLLMs, LGMs, and diffusion models to disentangle object generation from spatial placement. This enables unsupervised and flexible object insertion in 3D scenes without spatial priors. FreeInsert starts with an MLLM-based parser that extracts structured semantics, including object types, spatial relationships, and attachment regions, from user instructions. These semantics guide both the reconstruction of the inserted object for 3D consistency and the learning of its degrees of freedom. We leverage the spatial reasoning capabilities of MLLMs to initialize object pose and scale. A hierarchical, spatially aware refinement stage further integrates spatial semantics and MLLM-inferred priors to enhance placement. Finally, the appearance of the object is improved using the inserted-object image to enhance visual fidelity. Experimental results demonstrate that FreeInsert achieves semantically coherent, spatially precise, and visually realistic 3D insertions without relying on spatial priors, offering a user-friendly and flexible editing experience.