# Compos3D: Interactive Part-Based Composition for Creative Control in Generative 3D Models

arXiv: https://arxiv.org/abs/2607.12193 · HTML: https://mlsanity.com/paper/2607.12193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 28 of 28)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Learning Gradient Fields for Shape Generation](https://mlsanity.com/paper/2008.06520/) (2020)
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://mlsanity.com/paper/2203.09516/) (2022)
- [DreamEditor: Text-Driven 3D Scene Editing with Neural Fields](https://mlsanity.com/paper/2306.13455/) (2023)
- [Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions](https://mlsanity.com/paper/2211.13757/) (2022)
- [Discrete Point Flow Networks for Efficient Point Cloud Generation](https://mlsanity.com/paper/2007.10170/) (2020)
- [TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts](https://mlsanity.com/paper/2401.14828/) (2024)
- [EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria](https://mlsanity.com/paper/2309.13633/) (2023)
- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows](https://mlsanity.com/paper/2210.11603/) (2022)
- [PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions](https://mlsanity.com/paper/2308.05184/) (2023)
- [Spellburst: A Node-based Interface for Exploratory Creative Coding with Natural Language Prompts](https://mlsanity.com/paper/2308.03921/) (2023)
- [Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets](https://mlsanity.com/paper/2310.09985/) (2023)
- [WorldSmith: Iterative and Expressive Prompting for World Building with a Generative AI](https://mlsanity.com/paper/2308.13355/) (2023)
- [Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI](https://mlsanity.com/paper/2309.06379/) (2023)
- [VRCopilot: Authoring 3D Layouts with Generative AI Models in VR](https://mlsanity.com/paper/2408.09382/) (2024)
- [TactStyle: Generating Tactile Textures with Generative AI for Digital Fabrication](https://mlsanity.com/paper/2503.02007/) (2025)
- [InteRecon: Towards Reconstructing Interactivity of Personal Memorable Items in Mixed Reality](https://mlsanity.com/paper/2502.09973/) (2025)
- [HistoryPalette: Supporting Exploration and Reuse of Past Alternatives in Image Generation and Editing](https://mlsanity.com/paper/2501.04163/) (2025)

## Abstract (arXiv)

While generative AI has unlocked new opportunities for 3D content creation, current workflows often rely on multiple regenerations, which provides limited control and unpredictable outcomes. We present Compos3D, a system that introduces a compositional workflow for generative 3D modeling through remixing. Instead of repeatedly regenerating models, users generate multiple candidates from text or image prompts, select parts of interest via 2D image regions or 3D mesh segments, and assemble them into a coherent design. The system synthesizes these compositions into a refined 3D model, preserving high-level intent while resolving low-level geometry. To evaluate this approach, we conducted a controlled user study comparing remixing and regeneration workflows across both 2D and 3D modalities. Results show that the remixing workflow provides participants with greater creative control, stronger alignment with their intent, and higher satisfaction. We conclude with design recommendations for future AI-assisted 3D modeling workflows.