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

Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation

2019-01-16
Xia Li, Yen-Liang Lin, James Miller, Alex Cheon, Walt Dixon

Abstract

As we begin to consider modeling large, realistic 3D building scenes, it becomes necessary to consider a more compact representation over the polygonal mesh model. Due to the large amounts of annotated training data, which is costly to obtain, we leverage synthetic data to train our system for the satellite image domain. By utilizing the synthetic data, we formulate the building decomposition as an application of instance segmentation and primitive fitting to decompose a building into a set of primitive shapes. Experimental results on WorldView-3 satellite image dataset demonstrate the effectiveness of our 3D building modeling approach.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1901.05554

PDF

https://arxiv.org/pdf/1901.05554


Similar Posts

Comments