# AROS: Affordance Recognition with One-Shot Human Stances

arXiv: https://arxiv.org/abs/2210.11725 · HTML: https://mlsanity.com/paper/2210.11725/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [Generating 3D People in Scenes without People](https://mlsanity.com/paper/1912.02923/) (2019)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments](https://mlsanity.com/paper/1903.05690/) (2019)
- [SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization](https://mlsanity.com/paper/1912.05027/) (2019)
- [Binge Watching: Scaling Affordance Learning from Sitcoms](https://mlsanity.com/paper/1804.03080/) (2018)
- [Learning Action Maps of Large Environments via First-Person Vision](https://mlsanity.com/paper/1605.01679/) (2016)
- [Is That a Chair? Imagining Affordances Using Simulations of an Articulated Human Body](https://mlsanity.com/paper/1909.07572/) (2019)

## Abstract (arXiv)

We present AROS, a one-shot learning approach that uses an explicit representation of interactions between highly-articulated human poses and 3D scenes. The approach is one-shot as the method does not require re-training to add new affordance instances. Furthermore, only one or a small handful of examples of the target pose are needed to describe the interaction. Given a 3D mesh of a previously unseen scene, we can predict affordance locations that support the interactions and generate corresponding articulated 3D human bodies around them. We evaluate on three public datasets of scans of real environments with varied degrees of noise. Via rigorous statistical analysis of crowdsourced evaluations, results show that our one-shot approach outperforms data-intensive baselines by up to 80%.