# Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions

arXiv: https://arxiv.org/abs/2503.15898 · HTML: https://mlsanity.com/paper/2503.15898/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 55 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 30 of 50)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model](https://mlsanity.com/paper/2310.15110/) (2023)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [RealFusion: 360deg Reconstruction of Any Object from a Single Image](https://mlsanity.com/paper/2302.10663/) (2023)
- [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)
- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [Visual Semantic Role Labeling](https://mlsanity.com/paper/1505.04474/) (2015)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild](https://mlsanity.com/paper/2007.15649/) (2020)
- [Coherent Reconstruction of Multiple Humans from a Single Image](https://mlsanity.com/paper/2006.08586/) (2020)
- [One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer](https://mlsanity.com/paper/2303.16160/) (2023)
- [CHORE: Contact, Human and Object REconstruction from a single RGB image](https://mlsanity.com/paper/2204.02445/) (2022)
- [Detailed 2D-3D Joint Representation for Human-Object Interaction](https://mlsanity.com/paper/2004.08154/) (2020)
- [InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction](https://mlsanity.com/paper/2209.12354/) (2022)
- [Compositional Human-Scene Interaction Synthesis with Semantic Control](https://mlsanity.com/paper/2207.12824/) (2022)
- [PaStaNet: Toward Human Activity Knowledge Engine](https://mlsanity.com/paper/2004.00945/) (2020)
- [ChatPose: Chatting about 3D Human Pose](https://mlsanity.com/paper/2311.18836/) (2023)

## Built on by (most cited first, 13 of 13)

- [CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction](https://mlsanity.com/paper/2512.11988/) (2025)
- [TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions](https://mlsanity.com/paper/2510.14874/) (2025)
- [GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects](https://mlsanity.com/paper/2506.15483/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions](https://mlsanity.com/paper/2603.25791/) (2026)
- [Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction](https://mlsanity.com/paper/2512.00960/) (2025)
- [TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures](https://mlsanity.com/paper/2602.19679/) (2026)
- [End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction](https://mlsanity.com/paper/2603.14435/) (2026)
- [Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactions](https://mlsanity.com/paper/2512.00547/) (2025)
- [LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image](https://mlsanity.com/paper/2604.20800/) (2026)
- [Recovering Physically Plausible Human-Object Interactions from Monocular Videos](https://mlsanity.com/paper/2606.05359/) (2026)
- [Reconstructing Humans and Objects in Interaction using Large Reconstruction Models](https://mlsanity.com/paper/2608.27407/) (2026)
- [Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users](https://mlsanity.com/paper/2609.18406/) (2026)

## Abstract (arXiv)

Reconstructing human-object interactions (HOI) from single images is fundamental in computer vision. Existing methods are primarily trained and tested on indoor scenes due to the lack of 3D data, particularly constrained by the object variety, making it challenging to generalize to real-world scenes with a wide range of objects. The limitations of previous 3D HOI datasets were primarily due to the difficulty in acquiring 3D object assets. However, with the development of 3D reconstruction from single images, recently it has become possible to reconstruct various objects from 2D HOI images. We therefore propose a pipeline for annotating fine-grained 3D humans, objects, and their interactions from single images. We annotated 2.5k+ 3D HOI assets from existing 2D HOI datasets and built the first open-vocabulary in-the-wild 3D HOI dataset Open3DHOI, to serve as a future test set. Moreover, we design a novel Gaussian-HOI optimizer, which efficiently reconstructs the spatial interactions between humans and objects while learning the contact regions. Besides the 3D HOI reconstruction, we also propose several new tasks for 3D HOI understanding to pave the way for future work. Data and code will be publicly available at https://wenboran2002.github.io/3dhoi.