# LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

arXiv: https://arxiv.org/abs/2312.08963 · HTML: https://mlsanity.com/paper/2312.08963/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 79 of its 128 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 30 of 79)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [Learning to Detect Human-Object Interactions](https://mlsanity.com/paper/1702.05448/) (2017)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Detecting and Recognizing Human-Object Interactions](https://mlsanity.com/paper/1704.07333/) (2017)
- [Visual Semantic Role Labeling](https://mlsanity.com/paper/1505.04474/) (2015)
- [HOTR: End-to-End Human-Object Interaction Detection with Transformers](https://mlsanity.com/paper/2104.13682/) (2021)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)

## Built on by (most cited first, 30 of 49)

- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction](https://mlsanity.com/paper/2403.19652/) (2024)
- [DisPose: Disentangling Pose Guidance for Controllable Human Image Animation](https://mlsanity.com/paper/2412.09349/) (2024)
- [Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models](https://mlsanity.com/paper/2401.12978/) (2024)
- [InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2509.09555/) (2025)
- [GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding](https://mlsanity.com/paper/2411.19626/) (2024)
- [EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views](https://mlsanity.com/paper/2405.13659/) (2024)
- [PICO: Reconstructing 3D People In Contact with Objects](https://mlsanity.com/paper/2504.17695/) (2025)
- [InteractVLM: 3D Interaction Reasoning from 2D Foundational Models](https://mlsanity.com/paper/2504.05303/) (2025)
- [TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions](https://mlsanity.com/paper/2412.06334/) (2024)
- [HERO: Human Reaction Generation from Videos](https://mlsanity.com/paper/2503.08270/) (2025)
- [Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions](https://mlsanity.com/paper/2503.15898/) (2025)
- [SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets](https://mlsanity.com/paper/2504.06982/) (2025)
- [Grounding 3D Scene Affordance From Egocentric Interactions](https://mlsanity.com/paper/2409.19650/) (2024)
- [PEAR: Phrase-Based Hand-Object Interaction Anticipation](https://mlsanity.com/paper/2407.21510/) (2024)
- [FIction: 4D Future Interaction Prediction from Video](https://mlsanity.com/paper/2412.00932/) (2024)
- [Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors](https://mlsanity.com/paper/2505.24103/) (2025)
- [TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions](https://mlsanity.com/paper/2510.14874/) (2025)
- [FORCE: Physics-aware Human-object Interaction](https://mlsanity.com/paper/2403.11237/) (2024)
- [HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance](https://mlsanity.com/paper/2506.07209/) (2025)
- [DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models](https://mlsanity.com/paper/2501.08333/) (2025)
- [COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models](https://mlsanity.com/paper/2409.20502/) (2024)
- [GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images](https://mlsanity.com/paper/2505.06575/) (2025)
- [Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos](https://mlsanity.com/paper/2506.03440/) (2025)
- [O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2509.06233/) (2025)
- [Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction](https://mlsanity.com/paper/2512.00960/) (2025)
- [Decoupled Generative Modeling for Human-Object Interaction Synthesis](https://mlsanity.com/paper/2512.19049/) (2025)
- [Gloria: Consistent Character Video Generation via Content Anchors](https://mlsanity.com/paper/2603.29931/) (2026)
- [VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model](https://mlsanity.com/paper/2602.09638/) (2026)
- [Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation](https://mlsanity.com/paper/2606.30598/) (2026)

## Abstract (arXiv)

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interaction elements, e.g., human contact, object affordance, and human-object spatial relation, primarily from the perspective of either the human or the object. Which underexploit certain correlations between the interaction counterparts (human and object), and struggle to address the uncertainty in interactions. Actually, objects' functionalities potentially affect humans' interaction intentions, which reveals what the interaction is. Meanwhile, the interacting humans and objects exhibit matching geometric structures, which presents how to interact. In light of this, we propose harnessing these inherent correlations between interaction counterparts to mitigate the uncertainty and jointly anticipate the above interaction elements in 3D space. To achieve this, we present LEMON (LEarning 3D huMan-Object iNteraction relation), a unified model that mines interaction intentions of the counterparts and employs curvatures to guide the extraction of geometric correlations, combining them to anticipate the interaction elements. Besides, the 3D Interaction Relation dataset (3DIR) is collected to serve as the test bed for training and evaluation. Extensive experiments demonstrate the superiority of LEMON over methods estimating each element in isolation.