CVJan 16, 2019

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

arXiv:1901.05554v110 citations
AI Analysis

This addresses the need for efficient 3D building modeling in satellite imagery, though it appears incremental as it combines instance segmentation and primitive fitting with synthetic data.

The paper tackles the problem of modeling large 3D building scenes by proposing a compact representation using primitive shapes, trained with synthetic data to avoid costly annotated data. It demonstrates effectiveness on the WorldView-3 satellite image dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes