Structured Outdoor Architecture Reconstruction by Exploration and Classification

Zhang, Fuyang; Xu, Xiang; Nauata, Nelson; Furukawa, Yasutaka

doi:10.1109/iccv48922.2021.01220

Cited by 14 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment compared the proposed method with five current advanced methods: ASIP [ 29 ], that of Zhang et al [ 30 ], MonteFloor and Floor-SP. ASIP is an object vectorization algorithm, which uses a probability map to generate approximate shapes.…”

Section: Methodsmentioning

confidence: 99%

Reconstructing Floorplans from Point Clouds Using GAN

et al. 2023

View full text Add to dashboard Cite

This paper proposed a method for reconstructing floorplans from indoor point clouds. Unlike existing corner and line primitive detection algorithms, this method uses a generative adversarial network to learn the complex distribution of indoor layout graphics, and repairs incomplete room masks into more regular segmentation areas. Automatic learning of the structure information of layout graphics can reduce the dependence on geometric priors, and replacing complex optimization algorithms with Deep Neural Networks (DNN) can improve the efficiency of data processing. The proposed method can retain more shape information from the original data and improve the accuracy of the overall structure details. On this basis, the method further used an edge optimization algorithm to eliminate pixel-level edge artifacts that neural networks cannot perceive. Finally, combined with the constraint information of the overall layout, the method can generate compact floorplans with rich semantic information. Experimental results indicated that the algorithm has robustness and accuracy in complex 3D indoor datasets; its performance is competitive with those of existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Reconstructing Floorplans from Point Clouds Using GAN

et al. 2023

View full text Add to dashboard Cite

show abstract

“…We evaluate the proposed approach on two tasks (i.e., outdoor architecture and indoor floorplan reconstructions). For the outdoor task, we compare with five methods: ConvMPN [25], IP [16], Exp-cls [26], HAWP [24] and LETR [23]. The first three methods were demonstrated for the same outdoor task, while the latter two methods were for the wire-frame parsing.…”

Section: Competing Methodsmentioning

confidence: 99%

“…Albeit effective, optimization/search requires domain-specific algorithm design by hand and is a few orders of magnitude slower at test time. A recent approach by Zhang et al iterates exploration and classification steps to search for a better solution [26], while our approach is much faster and performs better.…”

Section: Hybrid Approachesmentioning

confidence: 99%

See 1 more Smart Citation

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction

Chen¹,

Qian²,

Furukawa³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Input imageOutput planar graph Outdoor Architecture Reconstruction Input image Output planar graph Indoor Floorplan ReconstructionHEAT HEAT Figure 1. HEAT takes a 2D raster image as an input and reconstructs a planar graph by an end-to-end transformer based neural architecture, for example, from a satellite image to an outdoor building architecture or from a point-density image to an indoor floorplan.

show abstract

“…After detecting geometric primitives and inferring primitivewise relationships, the information is formulated as an objective function [59], which is solved by MIP for the primitive assembly of the topology and semantics representation.…”

Section: B Indoor-space Primitive Assembly With Mipmentioning

confidence: 99%

Automated Semantics and Topology Representation of Residential-Building Space Using Floor-Plan Raster Maps

Wang

Jiang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Automatically representing the semantics and topology of indoor building spaces from floor-plans is necessary for many applications, such as architectural design and indoor renovations. Extensive studies have investigated reconstructing indoor spaces with semantics and topology using professional means (e.g., laser scanning and photogrammetry). Floor-plan raster maps are widely and freely available for various purposes. Nevertheless, there is little research on the semantic and topological representation of indoor elements from floor-plan raster maps. To fill this gap, we propose a method of automatically representing the semantics and topology of indoor spaces from floor-plan raster maps. The proposed method first identifies basic geometric primitives from floor-plans using a learning-based hierarchical segmentation approach. Second, the relationship between the detected geometric primitives is assembled into the planar structure representation with topological data using mixed integer programming. Finally, the floor-plan graph structure is checked and optimized to maintain consistency with a polygonal coordinate descent strategy, resulting in a correct representation of the semantics and topology of the indoor space. Comprehensive evaluations demonstrate that the proposed method effectively achieves superior performance in three different datasets. The proposed method allows for 3D model popups for better visualizations and direct architectural model manipulations of the interior building layouts computation.

show abstract

Structured Outdoor Architecture Reconstruction by Exploration and Classification

Cited by 14 publications

References 21 publications

Reconstructing Floorplans from Point Clouds Using GAN

Reconstructing Floorplans from Point Clouds Using GAN

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction

Automated Semantics and Topology Representation of Residential-Building Space Using Floor-Plan Raster Maps

Contact Info

Product

Resources

About