Review on Indoor RGB-D Semantic Segmentation with Deep Convolutional Neural Networks

TL;DR

This paper reviews the use of deep convolutional neural networks for indoor RGB-D semantic segmentation, discussing datasets, strategies, performance, challenges, and future directions in this emerging research area.

Contribution

It provides a comprehensive overview of recent methods, datasets, and performance evaluations in RGB-D indoor semantic segmentation using deep CNNs.

Findings

Summarizes key public datasets for RGB-D semantic segmentation.

Categorizes recent deep learning strategies for the task.

Evaluates current state-of-the-art performance and identifies challenges.

Abstract

Many research works focus on leveraging the complementary geometric information of indoor depth sensors in vision tasks performed by deep convolutional neural networks, notably semantic segmentation. These works deal with a specific vision task known as "RGB-D Indoor Semantic Segmentation". The challenges and resulting solutions of this task differ from its standard RGB counterpart. This results in a new active research topic. The objective of this paper is to introduce the field of Deep Convolutional Neural Networks for RGB-D Indoor Semantic Segmentation. This review presents the most popular public datasets, proposes a categorization of the strategies employed by recent contributions, evaluates the performance of the current state-of-the-art, and discusses the remaining challenges and promising directions for future works.