# CoopDiff: Anticipating 3D Human-object Interactions via Contact-consistent Decoupled Diffusion

arXiv: https://arxiv.org/abs/2508.07162 · HTML: https://mlsanity.com/paper/2508.07162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions](https://mlsanity.com/paper/2212.07555/) (2022)
- [SAGA: Stochastic Whole-Body Grasping with Contact](https://mlsanity.com/paper/2112.10103/) (2021)
- [Context-aware Human Motion Prediction](https://mlsanity.com/paper/1904.03419/) (2019)
- [NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis](https://mlsanity.com/paper/2307.07511/) (2023)
- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [Object pop-up: Can we infer 3D objects and their poses from human interactions alone?](https://mlsanity.com/paper/2306.00777/) (2023)
- [Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer](https://mlsanity.com/paper/2404.04819/) (2024)
- [AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation](https://mlsanity.com/paper/2410.07164/) (2024)
- [Guiding Human-Object Interactions with Rich Geometry and Relations](https://mlsanity.com/paper/2503.20172/) (2025)
- [Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions](https://mlsanity.com/paper/2206.12612/) (2022)
- [GEARS: Local Geometry-aware Hand-object Interaction Synthesis](https://mlsanity.com/paper/2404.01758/) (2024)
- [ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation](https://mlsanity.com/paper/2503.13130/) (2025)
- [HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes](https://mlsanity.com/paper/2407.02633/) (2024)
- [Predicting the Physical Dynamics of Unseen 3D Objects](https://mlsanity.com/paper/2001.06291/) (2020)
- [Interactive Visual Task Learning for Robots](https://mlsanity.com/paper/2312.13219/) (2023)

## Abstract (arXiv)

3D human-object interaction (HOI) anticipation aims to predict the future motion of humans and their manipulated objects, conditioned on the historical context. Generally, the articulated humans and rigid objects exhibit different motion patterns, due to their distinct intrinsic physical properties. However, this distinction is ignored by most of the existing works, which intend to capture the dynamics of both humans and objects within a single prediction model. In this work, we propose a novel contact-consistent decoupled diffusion framework CoopDiff, which employs two distinct branches to decouple human and object motion modeling, with the human-object contact points as shared anchors to bridge the motion generation across branches. The human dynamics branch is aimed to predict highly structured human motion, while the object dynamics branch focuses on the object motion with rigid translations and rotations. These two branches are bridged by a series of shared contact points with consistency constraint for coherent human-object motion prediction. To further enhance human-object consistency and prediction reliability, we propose a human-driven interaction module to guide object motion modeling. Extensive experiments on the BEHAVE and Human-object Interaction datasets demonstrate that our CoopDiff outperforms state-of-the-art methods.