Overview

Human motion generation studies how to synthesize or edit body movement for animation, avatars, interaction, and humanoid robots. Common approaches use diffusion or flow-matching models, autoregressive and masked motion tokens, and structured representations of body parts or joint trajectories; retrieval, planning, and physics-based refinement can add control. Text-to-motion is often tested on HumanML3D and KIT-ML, while dance and speech-driven gestures use benchmarks such as AIST++ and BEAT. A central challenge is balancing semantic accuracy, natural and diverse motion, physical plausibility, and precise control—especially for long or real-time sequences, where evaluation metrics may not reflect human judgments or successful execution.

Latest papers

CardsList

309 papers20 papers in the last four weeks, down 47% on the four weeks before. 0.2% of all new papers.

  1. UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation

    Aug 10, 2026Yilei Hua, Beibei Jing, Ce Zheng +3Flow MatchingText-to-Motion Generation

  2. VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation

    Aug 6, 2026Lala Shakti Swarup Ray, Vitor Fortes Rey, Mengxi Liu +2Human Activity RecognitionSynthetic Data Generation

  3. Tired Actor: Fatigue-Informed Character Control

    Aug 4, 2026Shengyuan Zhang, Xinpeng Liu, Muchun Niu +5Human Motion GenerationImitation Learning

  4. Surface Keypoint Representation for Multi-Object and Articulated Human-Object Interaction Generation

    Aug 4, 2026Xiaogang Peng, Zeyu Han, Zichong Meng +4HOI GenerationHuman Motion Generation

  5. DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units

    Aug 4, 2026Haoyu Gu, Haotian Lu, Jingrun Du +1Human Motion Generation

  6. StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring

    Aug 3, 2026Xiangyue Zhang, Jianfang Li, Jiaxu Zhang +2Human Motion GenerationCo-Speech Gesture Generation

  7. MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

    Jul 31, 2026Yifei Zhu, Dafei Qin, Zijiao Zeng +4Self-Supervised LearningText-to-Motion Generation

  8. MUGEN: A Unified Framework for Efficient Motion Understanding and Generation

    Jul 30, 2026Zhankai Ye, Yukai Jin, Bingyang Wei +5Representation LearningHuman Motion Generation

  9. MoSAIC: Aligned Intervention Supervision for Part-Local Motion Style Transfer

    Jul 28, 2026Nazanin Amini, Kevin DesaiHuman Motion GenerationDiffusion Models

  10. STEER: Steerable Dyadic Head Avatars

    Jul 26, 2026Kartik Teotia, Helge Rhodin, Hyeongwoo Kim +2Human Motion Generation3D Avatar Generation

  11. HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis

    Jul 19, 2026Lingwei Dang, Juntong Li, Zonghan Li +5Multi-View ConsistencyMulti-View Video Generation

  12. MIME: Multimodal Interactive Motion Encoder

    Jul 18, 2026Addison Zucek, Prerit Gupta, Kamila Kuatova +1Text-to-Motion GenerationCross-Modal Alignment

  13. A Diffusion-Based Kinematics and Dynamics Model for 3D Sign Language Production

    Jul 16, 2026Emanuele Colonna, Moises Diaz, Gennaro Vessio +2Physics-Informed Diffusion ModelsHuman Motion Generation

  14. Music-to-Dance Generation via Atomic Movements

    Jul 15, 2026Xinhao Cai, Yixuan Sun, Minghang Zheng +4Human Motion Generation

  15. MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

    Jul 15, 2026Zhongyi Zhang, Guangyuan Wang, Li Hu +6Identity-Preserving Video GenerationHuman Motion Generation

  16. Classifying daily activities needs posture, reconstructing them needs motion

    Jul 14, 2026Arefeh Farahmandi, Gunnar BlohmSkeleton-Based Action RecognitionHuman Activity Recognition

  17. GNOCHI: Generative Neural mOdel for Close Human-Human Interactions

    Jul 11, 2026Gonzalo Gómez-Nogales, Marc Comino-Trinidad, Andrés Casado-Elvira +1Human Motion GenerationHuman-Human-Object Interaction Generation

  18. Neural Motion Blending Across Arbitrary Character Topologies

    Jul 11, 2026Luca Cazzola, Giulia Martinelli, Nicola ConciHuman Motion Generation

  19. Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors

    Jul 11, 2026Zikai Huang, Siyue Chen, Xuemiao Xu +4Disentangled Representation LearningHuman Motion Generation

  20. ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

    Jul 9, 2026Kaifeng Zhao, Mathis Petrovich, Haotian Zhang +3Text-to-Motion GenerationHuman Motion Generation

  21. GIRAF: Towards Generalizable Human Interactions with Articulated Objects

    Jul 8, 2026Xiaohan Zhang, Sebastian Starke, Alexander Winkler +3HOI GenerationText-to-Motion Generation

  22. Generating Personalized Lower-Limb Kinematics Across Walking Speeds Using Subject-Conditioned Diffusion

    Jul 8, 2026Diya Dinesh, Adrian Krieger, Changseob Song +3Gait AnalysisHuman Motion Generation

  23. Towards Real-World Wearable Motion Reconstruction

    Jul 8, 2026Andrea Boscolo Camiletto, Rishabh Dabral, Eduardo Alvarado +33D ReconstructionHuman Motion Generation

  24. Prior-First, Condition-Second: Scalable and Controllable Hand Motion Completion

    Jul 7, 2026Mingyi Shi, Xuelin Chen, Taku KomuraAutoregressive Motion GenerationHuman Motion Generation

  25. DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction

    Jul 7, 2026Jiakun Li, Zhe Li, Wenqiang Wu +4Text-to-Motion GenerationHuman Motion Generation

  26. ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions

    Jul 7, 2026Huakun Liu, Qing Yu, Kent Fujiwara +2Motion Diffusion ModelsHuman Motion Generation

  27. ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments

    Jul 2, 2026Lu Pan, Hongwei ZhaoHuman Behavior SimulationHuman Motion Generation