# Pi-HOC: Pairwise 3D Human-Object Contact Estimation

arXiv: https://arxiv.org/abs/2604.12923 · HTML: https://mlsanity.com/paper/2604.12923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [HOTR: End-to-End Human-Object Interaction Detection with Transformers](https://mlsanity.com/paper/2104.13682/) (2021)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [CHORE: Contact, Human and Object REconstruction from a single RGB image](https://mlsanity.com/paper/2204.02445/) (2022)
- [Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer](https://mlsanity.com/paper/2112.01838/) (2021)
- [On Self-Contact and Human Pose](https://mlsanity.com/paper/2104.03176/) (2021)
- [Compositional Human-Scene Interaction Synthesis with Semantic Control](https://mlsanity.com/paper/2207.12824/) (2022)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [DECO: Dense Estimation of 3D Human-Scene Contact In The Wild](https://mlsanity.com/paper/2309.15273/) (2023)
- [LEMON: Learning 3D Human-Object Interaction Relation from 2D Images](https://mlsanity.com/paper/2312.08963/) (2023)
- [Detecting Human-Object Contact in Images](https://mlsanity.com/paper/2303.03373/) (2023)
- [Learning Complex 3D Human Self-Contact](https://mlsanity.com/paper/2012.10366/) (2020)
- [Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory](https://mlsanity.com/paper/2309.03696/) (2023)
- [EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2411.14280/) (2024)
- [HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance](https://mlsanity.com/paper/2205.05677/) (2022)
- [Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer](https://mlsanity.com/paper/2404.04819/) (2024)
- [Joint Optimization for 4D Human-Scene Reconstruction in the Wild](https://mlsanity.com/paper/2501.02158/) (2025)
- [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)
- [PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image](https://mlsanity.com/paper/2510.11649/) (2025)
- [Locality-Aware Zero-Shot Human-Object Interaction Detection](https://mlsanity.com/paper/2505.19503/) (2025)

## Abstract (arXiv)

Resolving real-world human-object interactions in images is a many-to-many challenge, in which disentangling fine-grained concurrent physical contact is particularly difficult. Existing semantic contact estimation methods are either limited to single-human settings or require object geometries (e.g., meshes) in addition to the input image. Current state-of-the-art leverages powerful VLM for category-level semantics but struggles with multi-human scenarios and scales poorly in inference. We introduce Pi-HOC, a single-pass, instance-aware framework for dense 3D semantic contact prediction of all human-object pairs. Pi-HOC detects instances, creates dedicated human-object (HO) tokens for each pair, and refines them using an InteractionFormer. A SAM-based decoder then predicts dense contact on SMPL human meshes for each human-object pair. On the MMHOI and DAMON datasets, Pi-HOC significantly improves accuracy and localization over state-of-the-art methods while achieving 20x higher throughput. We further demonstrate that predicted contacts improve SAM-3D image-to-mesh reconstruction via a test-time optimization algorithm and enable referential contact prediction from language queries without additional training.