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. Learning to Generate Human-Human-Object Interactions from Textual Descriptions

    Nov 25, 2025Jeonghyeon Na, Sangwon Baik, Inhee Lee +2HOI GenerationHuman Motion Generation

  2. LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes

    Aug 23, 2025Haozhuo Zhang, Jingkai Sun, Michele Caprio +5Human Motion GenerationAdversarial Motion Prior

  3. CoMPAS3D: A Dataset and Benchmark for Interactive Motion

    Jul 25, 2025Bermet Burkanova, Yasaman Etesam, Payam Jome Yazdian +5Human Motion GenerationHuman Motion Understanding

  4. MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles

    May 30, 2025Mingyi Shi, Wei Liu, Jidong Mei +4Human Motion GenerationMotion Retargeting

  5. Linear Multi-granular Body Modeling for Text-Driven Motion Generation

    Mar 10, 2025Xingzu Zhan, Genpei Zhang, Chen Xie +3Text-to-Motion GenerationHuman Motion Generation

  6. BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

    Nov 28, 2024Seong-Eun Hong, Soobin Lim, Juyeong Hwang +2Text-to-Motion GenerationHuman Motion Generation

  7. EgoGen: An Egocentric Synthetic Data Generator

    Jan 16, 2024Gen Li, Kaifeng Zhao, Siwei Zhang +5Synthetic Data GenerationHuman Motion Generation

  8. AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction

    Jan 10, 2024Sarmad Idrees, Seokman Sohn, Jongeun ChoiTransformerHuman Motion Generation