Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

August 2020

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

Authors:

Jason Y. Zhang, Sam Pepose, Hanbyul Joo, Deva Ramanan, Jitendra Malik, and Angjoo Kanazawa
Conference Paper
Proceedings of (ECCV) European Conference on Computer Vision

Abstract:

We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment. Notably, our method runs on datasets without any scene- or object-level 3D supervision. Our key insight is that considering humans and objects jointly gives rise to “3D common sense” constraints that can be used to resolve ambiguity. In particular, we introduce a scale loss that learns the distribution of object size from data; an occlusion-aware silhouette re-projection loss to optimize object pose; and a human-object interaction loss to capture the spatial layout of objects with which humans interact. We empirically validate that our constraints dramatically reduce the space of likely 3D spatial configurations. We demonstrate our approach on challenging, in-the-wild images of humans interacting with large objects (such as bicycles, motorcycles, and surfboards) and handheld objects (such as laptops, tennis rackets, and skateboards). We quantify the ability of our approach to recover human-object arrangements and outline remaining challenges in this relatively unexplored domain. The project webpage can be found at
https://jasonyzhang.com/phosa.

Notes:

We thank Georgia Gkioxari and Shubham Tulsiani for insightful discussion and Victoria Dean and Gengshan Yang for useful feedback. We also thank Senthil Purushwalkam for deadline reminders. This work was funded in part by the CMU Argo AI Center for Autonomous Vehicle Research.
@conference{Zhang-2020-126824,
author = {Jason Y. Zhang And Sam Pepose And Hanbyul Joo And Deva Ramanan And Jitendra Malik And Angjoo Kanazawa},
title = {Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2020},
month = {August},
pages = {34 - 51},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.