Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

TL;DR

This survey reviews recent advances in indoor 2.5D/3D scene understanding for autonomous agents, covering data representations, techniques, and evaluation metrics, highlighting challenges and future research directions.

Contribution

It provides a comprehensive overview of methods, datasets, and evaluation metrics for indoor scene understanding, and categorizes recent techniques within a unified taxonomy.

Findings

Comparison of datasets and data representations

Analysis of state-of-the-art techniques across tasks

Identification of current challenges and future directions

Abstract

With the availability of low-cost and compact 2.5/3D visual sensing devices, computer vision community is experiencing a growing interest in visual scene understanding of indoor environments. This survey paper provides a comprehensive background to this research topic. We begin with a historical perspective, followed by popular 3D data representations and a comparative analysis of available datasets. Before delving into the application specific details, this survey provides a succinct introduction to the core technologies that are the underlying methods extensively used in the literature. Afterwards, we review the developed techniques according to a taxonomy based on the scene understanding tasks. This covers holistic indoor scene understanding as well as subtasks such as scene classification, object detection, pose estimation, semantic segmentation, 3D reconstruction, saliency detection, physics-based reasoning and affordance prediction. Later on, we summarize the performance metrics used for evaluation in different tasks and a quantitative comparison among the recent state-of-the-art techniques. We conclude this review with the current challenges and an outlook towards the open research problems requiring further investigation.