mlsanityData to 14 Oct 2026

LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment

arXiv 2403.13307 ↗First posted 20 Mar 2024cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Language-guided scene-aware human motion generation has great significance for entertainment and robotics. In response to the limitations of existing datasets, we introduce LaserHuman, a pioneering dataset engineered to revolutionize Scene-Text-to-Motion research. LaserHuman stands out with its inclusion of genuine human motions within 3D environments, unbounded free-form natural language descriptions, a blend of indoor and outdoor scenarios, and dynamic, ever-changing scenes. Diverse modalities of capture data and rich annotations present great opportunities for the research of conditional motion generation, and can also facilitate the development of real-life applications. Moreover, to generate semantically consistent and physically plausible human motions, we propose a multi-conditional diffusion model, which is simple but effective, achieving state-of-the-art performance on existing datasets.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 46 of its 58 references that are in the map. First posted on arXiv 20 Mar 2024.

Builds on

46 of 58 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2020Point Transformercited by 1,470
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  7. 2022Human Motion Diffusion Modelcited by 1,080
  8. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  9. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  10. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 575
  11. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
  12. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
34 more
  1. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  2. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 408
  3. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  4. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  5. 2023Human Motion Diffusion as a Generative Priorcited by 357
  6. 2016The KIT Motion-Language Datasetcited by 338
  7. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  8. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 287
  9. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 265
  10. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  11. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 239
  12. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
  13. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  14. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  15. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 182
  16. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 158
  17. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  18. 2020Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenescited by 135
  19. 2022COUCH: Towards Controllable Human-Chair Interactionscited by 135
  20. 2019Generating 3D People in Scenes without Peoplecited by 127
  21. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  22. 2023Human Motion Generation: A Surveycited by 96
  23. 2023Unified Human-Scene Interaction via Prompted Chain-of-Contactscited by 94
  24. 2022Compositional Human-Scene Interaction Synthesis with Semantic Controlcited by 83
  25. 2023CIRCLE: Capture In Rich Contextual Environmentscited by 79
  26. 2020Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesiscited by 64
  27. 2023C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characterscited by 55
  28. 2023SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environmentscited by 47
  29. 2022LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensorscited by 44
  30. 2022HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDARcited by 38
  31. 2023CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactionscited by 27
  32. 2024LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environmentcited by 20
  33. 2023Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoningcited by 10
  34. 2023Language-driven Scene Synthesis using Multi-conditional Diffusion Modelcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 14; 2026: 9.

33 papers.

Sort:

By area:

  1. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  2. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregressioncited by 85
  3. 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 72
  4. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 68
  5. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 64
  6. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  7. 2025Absolute Coordinates Make Motion Generation Easycited by 29
  8. 2025A Survey on Human Interaction Motion Generationcited by 25
  9. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 18
  10. 2025SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidancecited by 16
  11. 2024SCENIC: Scene-aware Semantic Navigation with Instruction-guided Controlcited by 13
  12. 2024SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generationcited by 12
21 more
  1. 2025CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objectscited by 12
  2. 2025MOSPA: Human Motion Generation Driven by Spatial Audiocited by 12
  3. 2025Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generationcited by 11
  4. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  5. 2024Move-in-2D: 2D-Conditioned Human Motion Generationcited by 8
  6. 20253D Human Interaction Generation: A Surveycited by 7
  7. 2025EgoReAct: Egocentric Video-Driven 3D Human Reaction Generationcited by 7
  8. 2025HIS-GPT: Towards 3D Human-In-Scene Multimodal Understandingcited by 6
  9. 2025GenHSI: Controllable Generation of Human-Scene Interaction Videoscited by 6
  10. 2026UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priorscited by 5
  11. 2024COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Modelscited by 3
  12. 2026SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokenscited by 3
  13. 2024Towards Practical Human Motion Prediction with LiDAR Point Cloudscited by 2
  14. 2026Visually-grounded Humanoid Agentscited by 2
  15. 2026Dex2HOI: Dexterous Bimanual Two-Object Interaction Generationcited by 2
  16. 2026Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillationcited by 1
  17. 2026ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Datacited by 1
  18. 2026MoSAT: Human Motion Generation from Spatial Audio and Textual Descriptioncited by 1
  19. 2025SceneAdapt: Scene-aware Adaptation of Human Motion Diffusioncited by 0
  20. 2026EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversalcited by 0
  21. 2026Multi-Modal Controlled Coherent Motion Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes
  2. 2024Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
  3. 2024Generating Human Motion in 3D Scenes from Text Descriptions
  4. 2024Generating Human Interaction Motions in Scenes with Text Control
  5. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
  6. 2023Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
  7. 2023Controllable Human-Object Interaction Synthesis
  8. 2024The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion