HOI Generation

HOI: Human-Object Interaction

Overview

Human-object interaction generation studies how to create plausible motion and visual sequences in which people grasp, manipulate, carry, or otherwise interact with objects. Common approaches use diffusion and flow-matching models conditioned on text, images, poses, or sparse video controls, often adding contact maps, affordances, 3D geometry, or physics-based refinement. Researchers evaluate motion and video on datasets such as GRAB, OakInk, ARCTIC, and BEHAVE, while also exploring multi-person interactions and transfer to robot manipulation. A central challenge is balancing semantic control and visual quality with accurate contact, physical plausibility, and generalization to unseen objects and scenes, especially when paired training data is scarce.

Latest papers

CardsList

87 papers5 papers in the last four weeks, down 58% on the four weeks before. 0.0% of all new papers.

  1. GRAZE: Text-Free Grasp Synthesis for Unseen Objects from Human Gaze

    Nov 16, 2026Jeongho Lee, Boeun Kim, Hyung Jin Chang +2HOI GenerationRobotic Grasping

  2. InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction

    Nov 8, 2026Yude Zou, Yifei Yao, Yiwei Hao +2HOI GenerationGoal-Conditioned Planning

  3. TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds

    Nov 4, 2026Jiaao Yu, Yanjian Zhang, Haoyang Jiang +3Controllable Video GenerationReal-Time Interactive Video Generation

  4. World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction Generation

    Oct 20, 2026Jiushu Li, Haoran Wang, Yumeng Liu +4HOI Generation

  5. EmbodyHOI: Embodiment-Aware Generation of Hand-Object Interactions for Humanoid Dexterous Manipulation

    Oct 19, 2026Chaitanya Chawla, Kartik Sharma, Ananya Bal +2HOI GenerationHumanoid Robotics

  6. BUMP: Body-driven Unified Multi-object Physics for HOI Synthesis

    Oct 19, 2026Wonjung Woo, Hyeonwoo Kim, Hanbyul JooHOI GenerationHuman Motion Generation

  7. ULIFLOW: Unified Latent Human-Object Interaction Flow

    Oct 16, 2026Wenqi Cai, Chunzhi Gu, Weichen Zhou +5HOI GenerationHuman Motion Generation

  8. MFlowHOI: Whole-Body Human-Object Interaction Generation via Part-Aware MeanFlow

    Oct 12, 2026Qiang He, Yonghao Zhang, Yinda Zhang +7HOI GenerationOne-Step Generative Modeling

  9. Learning Dynamic Grasping

    Oct 10, 2026Nga Kiu Kelly Ho, Yilin Liu, Hao Xu +1HOI GenerationHuman Motion Generation

  10. MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances

    Oct 8, 2026Mingyuan Lei, Yoonchang Sung, Tat-Jen ChamHOI Generation

  11. VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation

    Oct 7, 2026Zhuo Chen, Yihua Cheng, Aleš Leonardis +1Hand-Object InteractionHOI Generation

  12. COSMI: COmpositional Synthesis of Multi-object Interactions

    Oct 2, 2026Daniel Eskandar, Ilya A. Petrov, Gerard Pons-MollHOI GenerationMultimodal Diffusion Models

  13. Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation

    Sep 29, 2026Hongjia Zhai, Xiyu Zhang, Haoran Zhang +5HOI GenerationExocentric-to-Egocentric Video Generation

  14. PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation

    Sep 29, 2026Chuqiao Li, Xianghui Xie, Yong Cao +2HOI GenerationText-to-Motion Generation

  15. Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation

    Sep 29, 2026Zihan Wang, Zhen Wu, Pieter Abbeel +6HOI GenerationHumanoid Loco-Manipulation

  16. Harnessing Coupled Stream Completion For Human-Object Interaction Modeling

    Sep 26, 2026Dawei Guan, Di Yang, Jiangtao WangHOI GenerationMotion Representation Learning

  17. LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction

    Sep 17, 2026Zeyu Han, Zichong Meng, Julian Tanke +8HOI GenerationHuman Motion Generation

  18. InterMASH: A Unified Geometric Representation for Grasp Synthesis

    Sep 16, 2026Xuanze Yang, Yumeng Liu, Haiyang Xin +5HOI GenerationRobotic Grasping

  19. Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions

    Sep 15, 2026Liu Cao, Xingze Wu, Jingzhi Cui +4HOI GenerationHumanoid Loco-Manipulation

  20. HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation

    Aug 15, 2026Yihong Ji, Jinsong Zhang, He Hu +1HOI GenerationHuman Motion Generation

  21. RGB-D Video Generation for Improving Human-to-Robot Object Handover Prediction

    Aug 13, 2026Tianyu Sun, Zhoujie Fu, Zihui Gao +2HOI GenerationSynthetic Data Generation for Robotics

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

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

  23. PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph

    Aug 3, 2026Zhenhao Zhang, Jiajun Zhang, Wei Min +1HOI GenerationDexterous Manipulation

  24. Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer

    Jul 30, 2026Weiquan Lin, Yu Deng, Shiyang Liu +6HOI GenerationHuman-Scene Interaction Reconstruction

  25. AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment

    Jul 24, 2026Ziyao Huang, Shunkai Li, Juan Cao +7HOI GenerationVideo Diffusion Models

  26. StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation

    Jul 22, 2026Zejing Rao, Haoxian Zhang, Xiaoqiang Liu +5HOI GenerationLong-Horizon Video Generation