# Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

arXiv: https://arxiv.org/abs/2403.18036 · HTML: https://mlsanity.com/paper/2403.18036/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 87 of its 106 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 87)

- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)

## Built on by (most cited first, 30 of 80)

- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI](https://mlsanity.com/paper/2404.09465/) (2024)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control](https://mlsanity.com/paper/2410.05260/) (2024)
- [Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data](https://mlsanity.com/paper/2507.07095/) (2025)
- [Human-Object Interaction from Human-Level Instructions](https://mlsanity.com/paper/2406.17840/) (2024)
- [ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model](https://mlsanity.com/paper/2412.14559/) (2024)
- [KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills](https://mlsanity.com/paper/2506.12851/) (2025)
- [Multi-modal Situated Reasoning in 3D Scenes](https://mlsanity.com/paper/2409.02389/) (2024)
- [The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion](https://mlsanity.com/paper/2412.10523/) (2024)
- [VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation](https://mlsanity.com/paper/2503.07135/) (2025)
- [PhyRecon: Physically Plausible Neural Scene Reconstruction](https://mlsanity.com/paper/2404.16666/) (2024)
- [CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement](https://mlsanity.com/paper/2406.19353/) (2024)
- [MaskControl: Spatio-Temporal Control for Masked Motion Synthesis](https://mlsanity.com/paper/2410.10780/) (2024)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations](https://mlsanity.com/paper/2505.02094/) (2025)
- [Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing](https://mlsanity.com/paper/2410.18977/) (2024)
- [UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation](https://mlsanity.com/paper/2508.01126/) (2025)
- [SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance](https://mlsanity.com/paper/2503.01291/) (2025)
- [SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization](https://mlsanity.com/paper/2412.05095/) (2024)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [EgoTwin: Dreaming Body and View in First Person](https://mlsanity.com/paper/2508.13013/) (2025)
- [LLM-enhanced Scene Graph Learning for Household Rearrangement](https://mlsanity.com/paper/2408.12093/) (2024)
- [SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation](https://mlsanity.com/paper/2411.19921/) (2024)
- [Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy](https://mlsanity.com/paper/2503.18349/) (2025)
- [MOSPA: Human Motion Generation Driven by Spatial Audio](https://mlsanity.com/paper/2507.11949/) (2025)
- [3EED: Ground Everything Everywhere in 3D](https://mlsanity.com/paper/2511.01755/) (2025)
- [SceneMI: Motion In-betweening for Modeling Human-Scene Interactions](https://mlsanity.com/paper/2503.16289/) (2025)
- [RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping](https://mlsanity.com/paper/2507.23734/) (2025)
- [HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion](https://mlsanity.com/paper/2507.01737/) (2025)

## Abstract (arXiv)

Despite significant advancements in text-to-motion synthesis, generating language-guided human motion within 3D environments poses substantial challenges. These challenges stem primarily from (i) the absence of powerful generative models capable of jointly modeling natural language, 3D scenes, and human motion, and (ii) the generative models' intensive data requirements contrasted with the scarcity of comprehensive, high-quality, language-scene-motion datasets. To tackle these issues, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals, especially when training with limited data lacking extensive language-scene-motion pairs. Our extensive experiments demonstrate that our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE. Additionally, we validate our model's exceptional generalization capabilities on a specially curated evaluation set featuring previously unseen descriptions and scenes.