Real-time Progressive 3D Semantic Segmentation for Indoor Scene

04/01/2018
by   Quang-Hieu Pham, et al.
0

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 real-time performance, our method is built atop small clusters of voxels 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.

READ FULL TEXT

page 2

page 11

page 12

page 13

page 14

research
05/01/2015

SynthCam3D: Semantic Understanding With Synthetic Indoor Scenes

We are interested in automatic scene understanding from geometric cues. ...
research
11/13/2020

Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

Analyzing scenes thoroughly is crucial for mobile robots acting in diffe...
research
07/17/2023

On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild

Aphid infestations can cause extensive damage to wheat and sorghum field...
research
06/03/2016

Reinforcement Learning for Semantic Segmentation in Indoor Scenes

Future advancements in robot autonomy and sophistication of robotics tas...
research
11/14/2016

Herding Generalizes Diverse M -Best Solutions

We show that the algorithm to extract diverse M -solutions from a Condit...
research
12/20/2022

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency

Masked Modeling (MM) has demonstrated widespread success in various visi...
research
04/23/2014

Find my mug: Efficient object search with a mobile robot using semantic segmentation

In this paper, we propose an efficient semantic segmentation framework f...

Please sign up or login with your details

Forgot password? Click here to reset