Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference
Published in
European Conference on Computer Vision(2019)External Links:
TL
TL;DR
A 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image, and a novel algorithm utilizing convolutional neural networks that detects geometric primitives and infers their relationships.
Abstract
This paper tackles a 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image. We provide a new benchmark with ground-truth annotations for 2,001 complex buildings across the cities of Atlanta, Paris, and Las Vegas. We also propose a novel algorithm utilizing 1) convolutional neural networks (CNNs) that detects geometric primitives and infers their relationships and 2) an integer programming (IP) that assembles the information into a 2D planar graph. While being a trivial task for human vision, the inference of a graph structure with an arbitrary topology is still an open problem for computer vision. Qualitative and quantitative evaluations demonstrate that our algorithm makes significant improvements over the current state-of-the-art, towards an intelligent system at the level of human perception. We will share code and data.
References32 items
1
Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest Path
2
DARNet: Deep Active Ray Network for Building Segmentation
3
PPGNet: Learning Point-Pair Graph for Line Segment Detection
4
End-to-End Wireframe Parsing
5