mlsanityData to 7 Oct 2026

A Survey on Human Interaction Motion Generation

arXiv 2503.12763 ↗First posted 17 Mar 2025cs.CV cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Humans inhabit a world defined by interactions -- with other humans, objects, and environments. These interactive movements not only convey our relationships with our surroundings but also demonstrate how we perceive and communicate with the real world. Therefore, replicating these interaction behaviors in digital systems has emerged as an important topic for applications in robotics, virtual reality, and animation. While recent advances in deep generative models and new datasets have accelerated progress in this field, significant challenges remain in modeling the intricate human dynamics and their interactions with entities in the external world. In this survey, we present, for the first time, a comprehensive overview of the literature in human interaction motion generation. We begin by establishing foundational concepts essential for understanding the research background. We then systematically review existing solutions and datasets across three primary interaction tasks -- human-human, human-object, and human-scene interactions -- followed by evaluation metrics. Finally, we discuss open research directions and future opportunities.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 212 of its 306 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

212 of 306 references.

References · 212

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2023GPT-4 Technical Reportcited by 18,132
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  8. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  11. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  12. 2017Neural Discrete Representation Learningcited by 4,650
38 more
  1. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  7. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  9. 2020Point Transformercited by 1,462
  10. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  11. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  12. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  13. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  14. 2022Human Motion Diffusion Modelcited by 1,062
  15. 2022Diffusion Models in Vision: A Surveycited by 1,008
  16. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  17. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  18. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  19. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 577
  20. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  21. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  22. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  23. 2020Jukebox: A Generative Model for Musiccited by 535
  24. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  25. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  26. 2024Large Language Models: A Surveycited by 506
  27. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  28. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 486
  29. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 479
  30. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 438
  31. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  32. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 397
  33. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  34. 2019Learning joint reconstruction of hands and manipulated objectscited by 377
  35. 2016Generating Videos with Scene Dynamicscited by 376
  36. 2023Human Motion Diffusion as a Generative Priorcited by 354
  37. 2016The KIT Motion-Language Datasetcited by 334
  38. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321

50 most cited of 212 All 212 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 15.

25 papers.

Sort:

By area:

  1. 2025SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Predictioncited by 26
  2. 2025DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modelingcited by 21
  3. 2025Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motionscited by 11
  4. 2025Motion Synthesis with Sparse and Flexible Keyjoint Controlcited by 9
  5. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  6. 2025GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objectscited by 7
  7. 2025Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Modelscited by 6
  8. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  9. 2026TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Sizecited by 4
  10. 2026Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learningcited by 4
  11. 2026ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generationcited by 3
  12. 2026Multimodal Priors-Augmented Text-Driven 3D Human-Object Interaction Generationcited by 2
13 more
  1. 2026SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokenscited by 2
  2. 2026PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generationcited by 1
  3. 2026Dex2HOI: Dexterous Bimanual Two-Object Interaction Generationcited by 1
  4. 2025ReactionMamba: Generating Short & Long Human Reaction Sequencescited by 0
  5. 2025A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniquescited by 0
  6. 2026TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generationcited by 0
  7. 2026ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreographycited by 0
  8. 2026PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordinationcited by 0
  9. 2026SalsaAgent: A multimodal embodied language model for interactive dance generationcited by 0
  10. 2026Social Structure Matters in 3D Human-Human Interaction Generationcited by 0
  11. 2026ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitionscited by 0
  12. 2026SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generationcited by 0
  13. 2026MIME: Multimodal Interactive Motion Encodercited by 0