papers AI Learner
The Github is limit! Click to go to the new site.

DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences

2019-04-25
Ameya Phalak, Zhao Chen, Darvin Yi, Khushi Gupta, Vijay Badrinarayanan, Andrew Rabinovich

Abstract

We present DeepPerimeter, a deep learning based pipeline for inferring a full indoor perimeter (i.e. exterior boundary map) from a sequence of posed RGB images. Our method relies on robust deep methods for depth estimation and wall segmentation to generate an exterior boundary point cloud, and then uses deep unsupervised clustering to fit wall planes to obtain a final boundary map of the room. We demonstrate that DeepPerimeter results in excellent visual and quantitative performance on the popular ScanNet and FloorNet datasets and works for room shapes of various complexities as well as in multiroom scenarios. We also establish important baselines for future work on indoor perimeter estimation, topics which will become increasingly prevalent as application areas like augmented reality and robotics become more significant.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.11595

PDF

http://arxiv.org/pdf/1904.11595


Similar Posts

Comments