PrimHOI: Compositional Human-Object Interaction via Reusable Primitives
Kai Jia, Tengyu Liu, Yixin Zhu, Mingtao Pei, Siyuan Huang
Abstract
Figure 1. Diverse HOI motions for complex tasks generated by PrimHOI. Given an unseen high-level task description, our PrimHOI plans and generates diverse HOI motions that fulfill task requirements through spatial and temporal composition of generalizable interaction primitives. These primitives capture repetitive local contact patterns from everyday interactions, enabling systematic reuse across different scenarios. PrimHOI achieves zero-shot transfer to unseen HOI tasks without requiring task-specific training data.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext e0b8a768-5a96-471d-947f-9bb86633a683Cited by top-tier papers3
- InterPrior: Scaling Generative Control for Physics-Based Human-Object InteractionsSirui Xu, Samuel Schulter, Morteza Ziyadi, Xialin He et al.CVPR 2026 · 14 citations
- Decoupled Generative Modeling for Human-Object Interaction SynthesisHwanhee Jung, Seunggwan Lee, Jeongyoon Yoon, SeungHyeon Kim et al.CVPR 2026 · 4 citations
- InterPhys: Physics-aware Human Motion Synthesis in a Dynamic SceneChaoyue Xing, Wei Mao, Miaomiao LiuCVPR 2026 · 1 citation
Builds on31
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- AMP: adversarial motion priors for stylized physics-based character controlXue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine et al.SIGGRAPH 2021 · 392 citations
- Perpetual Humanoid Control for Real-time Simulated AvatarsZhengyi Luo, Jinkun Cao, Alexander Winkler, Kris Kitani et al.ICCV 2023 · 256 citations
- Guided Motion Diffusion for Controllable Human Motion SynthesisKorrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn, Siyu TangICCV 2023 · 240 citations
Related papers
- Learning Transferable Human-Object Interaction Detector with Natural Language SupervisionSuchen Wang, Yueqi Duan, Henghui Ding, Yap-Peng Tan et al.CVPR 2022 · 66 citations
- Learning Object-Centric Motion Priors from Human for Robotic Dexterous ManipulationZhengdong Hong, Guofeng ZhangAAAI 2026
- LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand DiffusionMuchen Li, Sammy Christen, Chengde Wan, Yujun Cai et al.CVPR 2025
- Open-World Human-Object Interaction Detection via Multi-Modal PromptsJie Yang, Bingliang Li, Ailing Zeng, Lei Zhang et al.CVPR 2024 · 18 citations
- Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI DetectionYixin Guo, Yu Liu, Jianghao Li, Weimin Wang et al.ACM MM 2024 · 12 citations
