arXiv Analytics

Sign in

arXiv:1910.02527 [cs.CV]AbstractReferencesReviewsResources

3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera

Iro Armeni, Zhi-Yang He, JunYoung Gwak, Amir R. Zamir, Martin Fischer, Jitendra Malik, Silvio Savarese

Published 2019-10-06Version 1

A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, texture, etc.) be grounded and what should be its structure? Aspiring to have one unified structure that hosts diverse types of semantics, we follow the Scene Graph paradigm in 3D, generating a 3D Scene Graph. Given a 3D mesh and registered panoramic images, we construct a graph that spans the entire building and includes semantics on objects (e.g., class, material, and other attributes), rooms (e.g., scene category, volume, etc.) and cameras (e.g., location, etc.), as well as the relationships among these entities. However, this process is prohibitively labor heavy if done manually. To alleviate this we devise a semi-automatic framework that employs existing detection methods and enhances them using two main constraints: I. framing of query images sampled on panoramas to maximize the performance of 2D detectors, and II. multi-view consistency enforcement across 2D detections that originate in different camera locations.

Related articles: Most relevant | Search more
arXiv:2008.07817 [cs.CV] (Published 2020-08-18)
Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph
arXiv:2006.04569 [cs.CV] (Published 2020-06-08)
Person Re-identification in the 3D Space
arXiv:2206.11895 [cs.CV] (Published 2022-06-23)
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space