# GenZI: Zero-Shot 3D Human-Scene Interaction Generation

arXiv: https://arxiv.org/abs/2311.17737 · HTML: https://mlsanity.com/paper/2311.17737/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes](https://mlsanity.com/paper/2210.09729/) (2022)
- [Monocular Expressive Body Regression through Body-Driven Attention](https://mlsanity.com/paper/2008.09062/) (2020)
- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer](https://mlsanity.com/paper/2303.16160/) (2023)
- [Generating 3D People in Scenes without People](https://mlsanity.com/paper/1912.02923/) (2019)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Capturing Hands in Action using Discriminative Salient Points and Physics Simulation](https://mlsanity.com/paper/1506.02178/) (2015)

## Built on by (most cited first, 30 of 40)

- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction](https://mlsanity.com/paper/2403.19652/) (2024)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models](https://mlsanity.com/paper/2401.12978/) (2024)
- [BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects](https://mlsanity.com/paper/2412.05066/) (2024)
- [ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation](https://mlsanity.com/paper/2412.18600/) (2024)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [InterTrack: Tracking Human Object Interaction without Object Templates](https://mlsanity.com/paper/2408.13953/) (2024)
- [SuperDec: 3D Scene Decomposition with Superquadric Primitives](https://mlsanity.com/paper/2504.00992/) (2025)
- [InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing](https://mlsanity.com/paper/2505.24315/) (2025)
- [You Think, You ACT: The New Task of Arbitrary Text to Motion Generation](https://mlsanity.com/paper/2404.14745/) (2024)
- [FORCE: Physics-aware Human-object Interaction](https://mlsanity.com/paper/2403.11237/) (2024)
- [Target-Aware Video Diffusion Models](https://mlsanity.com/paper/2503.18950/) (2025)
- [HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance](https://mlsanity.com/paper/2506.07209/) (2025)
- [GenHSI: Controllable Generation of Human-Scene Interaction Videos](https://mlsanity.com/paper/2506.19840/) (2025)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception](https://mlsanity.com/paper/2506.01579/) (2025)
- [VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification](https://mlsanity.com/paper/2512.09646/) (2025)
- [COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models](https://mlsanity.com/paper/2409.20502/) (2024)
- [Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models](https://mlsanity.com/paper/2503.15996/) (2025)
- [Decoupled Generative Modeling for Human-Object Interaction Synthesis](https://mlsanity.com/paper/2512.19049/) (2025)
- [Open-Vocabulary Functional 3D Human-Scene Interaction Generation](https://mlsanity.com/paper/2601.20835/) (2026)
- [InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement](https://mlsanity.com/paper/2604.04843/) (2026)
- [Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects](https://mlsanity.com/paper/2410.01816/) (2024)
- [Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis](https://mlsanity.com/paper/2503.00371/) (2025)
- [Learning to Generate Human-Human-Object Interactions from Textual Descriptions](https://mlsanity.com/paper/2511.20446/) (2025)
- [Diverse 3D Human Pose Generation in Scenes based on Decoupled Structure](https://mlsanity.com/paper/2406.05691/) (2024)
- [3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications](https://mlsanity.com/paper/2410.10782/) (2024)

## Abstract (arXiv)

Can we synthesize 3D humans interacting with scenes without learning from any 3D human-scene interaction data? We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene. We then formulate a robust iterative optimization to synthesize the pose and shape of a 3D human model in the scene, guided by consistency with the 2D interaction hypotheses. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data, and allows for flexible control of the 3D interaction synthesis with easy-to-use text prompts. Extensive experiments show that our zero-shot approach has high flexibility and generality, making it applicable to diverse scene types, including both indoor and outdoor environments.