# Action-guided generation of 3D functionality segmentation data

arXiv: https://arxiv.org/abs/2511.23230 · HTML: https://mlsanity.com/paper/2511.23230/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects](https://mlsanity.com/paper/2006.13171/) (2020)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation](https://mlsanity.com/paper/2301.13166/) (2023)
- [PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI](https://mlsanity.com/paper/2404.09465/) (2024)
- [Learning to Generate Synthetic Data via Compositing](https://mlsanity.com/paper/1904.05475/) (2019)
- [CAGE: Controllable Articulation GEneration](https://mlsanity.com/paper/2312.09570/) (2023)
- [SceneCraft: Layout-Guided 3D Scene Generation](https://mlsanity.com/paper/2410.09049/) (2024)
- [Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data](https://mlsanity.com/paper/2112.00054/) (2021)
- [SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation](https://mlsanity.com/paper/2412.01801/) (2024)
- [ArtFormer: Controllable Generation of Diverse 3D Articulated Objects](https://mlsanity.com/paper/2412.07237/) (2024)
- [Functionality understanding and segmentation in 3D scenes](https://mlsanity.com/paper/2411.16310/) (2024)
- [Spot-Compose: A Framework for Open-Vocabulary Object Retrieval and Drawer Manipulation in Point Clouds](https://mlsanity.com/paper/2404.12440/) (2024)
- [Video Perception Models for 3D Scene Synthesis](https://mlsanity.com/paper/2506.20601/) (2025)
- [Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints](https://mlsanity.com/paper/2508.00558/) (2025)
- [Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement](https://mlsanity.com/paper/2511.11702/) (2025)
- [SynGen-Vision: Synthetic Data Generation for training industrial vision models](https://mlsanity.com/paper/2509.04894/) (2025)

## Built on by (most cited first, 2 of 2)

- [SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling](https://mlsanity.com/paper/2512.05343/) (2025)
- [FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents](https://mlsanity.com/paper/2609.20673/) (2026)

## Abstract (arXiv)

3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the second drawer of the cabinet near the bed''). Progress has been constrained by the scarcity of annotated real-world data, as collecting and labeling fine-grained 3D masks is prohibitively expensive. To address this limitation, we introduce SynthFun3D, the first method for generating 3D functionality segmentation data directly from action descriptions. Given an action description, SynthFun3D constructs a plausible 3D scene by retrieving objects with part-level annotations from a large-scale asset repository and arranging them under spatial and semantic constraints. SynthFun3D renders multi-view images and automatically identifies the target functional element, producing precise ground-truth masks without manual annotation. We demonstrate the effectiveness of the generated data by training a VLM-based 3D functionality segmentation model. Augmenting real-world data with our synthetic data consistently improves performance, with gains of +2.2 mAP, +6.3 mAR, and +5.7 mIoU over real-only training. This shows that action-guided synthetic data generation provides a scalable and effective complement to manual annotation for 3D functionality understanding. Project page: tev-fbk.github.io/synthfun3d.