CG-HOI: Contact-Guided 3D Human-Object Interaction Generation
Christian Diller, Angela Dai
摘要
Application to Objects in Static 3D Scene Scans Carry a plastic container Play with a yoga ball Lift a small table Carry a large box Move the chair sideways Figure 1. We present an approach to generate realistic 3D human-object interactions (HOIs), from a text description and given static object geometry to be interacted with (left). Our main insight is to explicitly model contact (visualized as colors on the body mesh, closer contact in red), in tandem with human and object sequences, in a joint diffusion process. In addition to synthesizing HOIs from text, we can also synthesize human motions conditioned on given object trajectories (top right), and generate interactions in static scene scans (bottom right).
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper65
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object InteractionSirui Xu, Ziyin Wang, Yu-Xiong Wang, Liangyan GuiNeurIPS 2024 · 被引用 78 次
- HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction AwarenessZihui Xue, Romy Luo, Changan Chen, Kristen GraumanNeurIPS 2024 · 被引用 29 次
- DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB ImageDaoyi Gao, Dávid Rozenberszki, Stefan Leutenegger, Angela DaiSIGGRAPH 2024 · 被引用 28 次
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated ObjectsHuaijin Pi, Zhi Cen, Zhiyang Dou, Taku KomuraNeurIPS 2025 · 被引用 14 次
- InterPrior: Scaling Generative Control for Physics-Based Human-Object InteractionsSirui Xu, Samuel Schulter, Morteza Ziyadi, Xialin He 等CVPR 2026 · 被引用 14 次
它引用的顶会 Paper56
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion ModelsAlexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam 等ICML 2022 · 被引用 4,691 次
- Planning with Diffusion for Flexible Behavior SynthesisMichael Janner, Yilun Du, Joshua B. Tenenbaum, Sergey LevineICML 2022 · 被引用 1,115 次
相关 Paper
- InterDiff: Generating 3D Human-Object Interactions with Physics-Informed DiffusionSirui Xu, Zhengyuan Li, Yu-Xiong Wang, Liang-Yan GuiICCV 2023 · 被引用 201 次
- Learning to Generate Human-Human-Object Interactions from Textual DescriptionsJeonghyeon Na, Sangwon Baik, Inhee Lee, Junyoung Lee 等NeurIPS 2025 · 被引用 3 次
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance ParsingJinlu Zhang, Yixin Chen, Zan Wang, Jie Yang 等CVPR 2025
- ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction GenerationLing-An Zeng, Guohong Huang, Yi-Lin Wei, Shengbo Gu 等CVPR 2025
- TriDi: Trilateral Diffusion of 3D Humans, Objects, and InteractionsIlia A. Petrov, Riccardo Marin, Julian Chibane, Gerard Pons-MollICCV 2025 · 被引用 1 次
