# InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

arXiv: https://arxiv.org/abs/2504.05303 · HTML: https://mlsanity.com/paper/2504.05303/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 76 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 30 of 62)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)

## Built on by (most cited first, 21 of 21)

- [PICO: Reconstructing 3D People In Contact with Objects](https://mlsanity.com/paper/2504.17695/) (2025)
- [CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction](https://mlsanity.com/paper/2512.11988/) (2025)
- [Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction](https://mlsanity.com/paper/2512.00960/) (2025)
- [ViHOI: Human-Object Interaction Synthesis with Visual Priors](https://mlsanity.com/paper/2603.24383/) (2026)
- [DecoDINO: 3D Human-Scene Contact Prediction with Semantic Classification](https://mlsanity.com/paper/2510.23203/) (2025)
- [TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures](https://mlsanity.com/paper/2602.19679/) (2026)
- [HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding](https://mlsanity.com/paper/2603.02329/) (2026)
- [End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction](https://mlsanity.com/paper/2603.14435/) (2026)
- [UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video](https://mlsanity.com/paper/2604.19923/) (2026)
- [DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation](https://mlsanity.com/paper/2604.20841/) (2026)
- [TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank](https://mlsanity.com/paper/2508.21795/) (2025)
- [CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives](https://mlsanity.com/paper/2512.14696/) (2025)
- [Pi-HOC: Pairwise 3D Human-Object Contact Estimation](https://mlsanity.com/paper/2604.12923/) (2026)
- [LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image](https://mlsanity.com/paper/2604.20800/) (2026)
- [Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos](https://mlsanity.com/paper/2605.14462/) (2026)
- [RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos](https://mlsanity.com/paper/2605.17014/) (2026)
- [Recovering Physically Plausible Human-Object Interactions from Monocular Videos](https://mlsanity.com/paper/2606.05359/) (2026)
- [GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image](https://mlsanity.com/paper/2608.28386/) (2026)
- [Harnessing Coupled Stream Completion For Human-Object Interaction Modeling](https://mlsanity.com/paper/2609.32551/) (2026)
- [PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video](https://mlsanity.com/paper/2610.00451/) (2026)
- [EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes](https://mlsanity.com/paper/2610.01210/) (2026)

## Abstract (arXiv)

We introduce InteractVLM, a novel method to estimate 3D contact points on human bodies and objects from single in-the-wild images, enabling accurate human-object joint reconstruction in 3D. This is challenging due to occlusions, depth ambiguities, and widely varying object shapes. Existing methods rely on 3D contact annotations collected via expensive motion-capture systems or tedious manual labeling, limiting scalability and generalization. To overcome this, InteractVLM harnesses the broad visual knowledge of large Vision-Language Models (VLMs), fine-tuned with limited 3D contact data. However, directly applying these models is non-trivial, as they reason only in 2D, while human-object contact is inherently 3D. Thus we introduce a novel Render-Localize-Lift module that: (1) embeds 3D body and object surfaces in 2D space via multi-view rendering, (2) trains a novel multi-view localization model (MV-Loc) to infer contacts in 2D, and (3) lifts these to 3D. Additionally, we propose a new task called Semantic Human Contact estimation, where human contact predictions are conditioned explicitly on object semantics, enabling richer interaction modeling. InteractVLM outperforms existing work on contact estimation and also facilitates 3D reconstruction from an in-the wild image. Code and models are available at https://interactvlm.is.tue.mpg.de.