Image semantic segmentation of indoor scenes: A survey

• Published in: Computer vision and image understanding Vol. 248; p. 104102
• Main Authors: Velastegui, Ronny, Tatarchenko, Maxim, Karaoglu, Sezer, Gevers, Theo
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.11.2024
• Subjects: Deep learning; Image semantic segmentation; Indoor semantic segmentation; Scene labeling; Deep learning; Image semantic segmentation; 41A10; Indoor semantic segmentation; 65D05; 65D17; Scene labeling; 41A05
• ISSN: 1077-3142
• DOI: 10.1016/j.cviu.2024.104102

This survey provides a comprehensive evaluation of various deep learning-based segmentation architectures. It covers a wide range of models, from traditional ones like FCN and PSPNet to more modern approaches like SegFormer and FAN. In addition to assessing the methods in terms of segmentation accuracy, we propose to also evaluate the methods in terms of temporal consistency and corruption vulnerability. Most of the existing surveys on semantic segmentation focus on outdoor datasets. In contrast, this survey focuses on indoor scenarios to enhance the applicability of segmentation methods in this specific domain. Furthermore, our evaluation consists of a performance analysis of the methods in prevalent real-world segmentation scenarios that pose particular challenges. These complex situations involve scenes impacted by diverse forms of noise, blur corruptions, camera movements, optical aberrations, among other factors. By jointly exploring the segmentation accuracy, temporal consistency, and corruption vulnerability in challenging real-world situations, our survey offers insights that go beyond existing surveys, facilitating the understanding and development of better image segmentation methods for indoor scenes. •Comprehensive evaluation of various deep learning-based segmentation architectures.•Evaluating temporal consistency and corruption vulnerability of segmentation models.•Semantic segmentation under noise, blur, optical aberrations, compression artifacts.•Improving the understanding of image segmentation methods for indoor scenes.