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

Source: [Pi-HOC: Pairwise 3D Human-Object Contact Estimation](<https://www.sota2.com/research/paper/69df1bc67d0172140ec7bbbc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-14T05:00:05.130Z

Authors: Sravan Chittupalli, Ayush Jain, Dong Huang

Published: 2026-04-14T16:09:56.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Contact Prediction on MMHOI (test)](<https://www.sota2.com/research/sota/semantic-contact-prediction-on-mmhoi-test.md>): Semantic Contact Prediction; MMHOI (test); F1 Score: 61.09.

- [Vertex-level human-scene contact prediction on DAMON (test)](<https://www.sota2.com/research/sota/vertex-level-human-scene-contact-prediction-on-damon-test.md>): Vertex-level human-scene contact prediction; DAMON (test); Precision: 64.49.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.12923>)

[PDF](<https://arxiv.org/pdf/2604.12923.pdf>)
