Real-Time Progressive 3D Semantic Segmentation for Indoor Scenes

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense reconstruction and semantic segmentation of 3D indoor scenes....

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE Winter Conference on Applications of Computer Vision (WACV) pp. 1089 - 1098
Main Authors Pham, Quang-Hieu, Hua, Binh-Son, Nguyen, Thanh, Yeung, Sai-Kit
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2019
Subjects
Image reconstruction
Image segmentation
Neural networks
Real-time systems
Semantics
Three-dimensional displays
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary:The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense reconstruction and semantic segmentation of 3D indoor scenes. To guarantee (near) real-time performance, our method is built atop an efficient super-voxel clustering method and a conditional random field with higher-order constraints from structural and object cues, enabling progressive dense semantic segmentation without any precomputation. We extensively evaluate our method on different indoor scenes including kitchens, offices, and bedrooms in the SceneNN and ScanNet datasets and show that our technique consistently produces state-of-the-art segmentation results in both qualitative and quantitative experiments.
DOI:10.1109/WACV.2019.00121