mlsanityData to 7 Oct 2026

Long-term Human Motion Prediction with Scene Context

arXiv 2007.03672 ↗First posted 7 Jul 2020cs.CVcited by 191

Not on the map. Why?

Abstract (arXiv)

Human movement is goal-directed and influenced by the spatial layout of the objects in the scene. To plan future human motion, it is crucial to perceive the environment -- imagine how hard it is to navigate a new room with lights off. Existing works on predicting human motion do not pay attention to the scene context and thus struggle in long-term prediction. In this work, we propose a novel three-stage framework that exploits scene context to tackle this task. Given a single scene image and 2D pose histories, our method first samples multiple human motion goals, then plans 3D human paths towards each goal, and finally predicts 3D human pose sequences following each path. For stable training and rigorous evaluation, we contribute a diverse synthetic dataset with clean annotations. In both synthetic and real datasets, our method shows consistent quantitative and qualitative improvements over existing methods.

Key facts. Cited by 191 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 41; 2023: 45; 2024: 40; 2025: 33; 2026: 6.

191 papers.

Sort:

By area:

  1. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  2. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 357
  3. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  4. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  5. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  6. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  7. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 156
  8. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  9. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  10. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 137
  11. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  12. 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
38 more
  1. 2022COUCH: Towards Controllable Human-Chair Interactionscited by 134
  2. 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 129
  3. 2022Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motioncited by 125
  4. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  5. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  6. 2022Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videoscited by 110
  7. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  8. 2023Human Motion Generation: A Surveycited by 95
  9. 2022Towards Diverse and Natural Scene-aware 3D Human Motion Synthesiscited by 91
  10. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  11. 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 89
  12. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  13. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  14. 2023CIRCLE: Capture In Rich Contextual Environmentscited by 79
  15. 2024Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordancecited by 79
  16. 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
  17. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 77
  18. 2021Multi-Person Extreme Motion Predictioncited by 74
  19. 2021Scene-aware Generative Network for Human Motion Synthesiscited by 70
  20. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  21. 2021Playing for 3D Human Recoverycited by 63
  22. 2021Multi-Person 3D Motion Prediction with Multi-Range Transformerscited by 63
  23. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 63
  24. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  25. 2023DECO: Dense Estimation of 3D Human-Scene Contact In The Wildcited by 54
  26. 2024ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactionscited by 54
  27. 2023Putting People in Their Place: Affordance-Aware Human Insertion into Scenescited by 53
  28. 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 53
  29. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  30. 2023Physically Plausible Full-Body Hand-Object Interaction Synthesiscited by 52
  31. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 52
  32. 2023Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environmentscited by 51
  33. 2023EPIC Fields: Marrying 3D Geometry and Video Understandingcited by 49
  34. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  35. 2022MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labelscited by 45
  36. 2023Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Modelscited by 43
  37. 2021AGENT: A Benchmark for Core Psychological Reasoningcited by 42
  38. 2023I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactionscited by 42

50 most cited of 191 All 191 (JSON)