5 Hits in 0.81 sec

Graph2Plan: Learning Floorplan Generation from Layout Graphs [article]

Ruizhen Hu, Zeyu Huang, Yuhan Tang, Oliver van Kaick, Hao Zhang, Hui Huang
2020 pre-print
The core component of our learning framework is a deep neural network, Graph2Plan, which converts a layout graph, along with a building boundary, into a floorplan that fulfills both the layout and boundary  ...  For each retrieved layout graph, along with the input boundary, Graph2Plan first generates a corresponding raster floorplan image, and then a refined set of boxes representing the rooms.  ...  Our deep neural network Graph2Plan is a learning framework for automated floorplan generation from layout graphs.  ... 
doi:10.1145/3386569.3392391 arXiv:2004.13204v1 fatcat:qnr3paus5vgzfnjswra5mqotqe

iPLAN: Interactive and Procedural Layout Planning [article]

Feixiang He, Yanlong Huang, He Wang
2022 arXiv   pre-print
Recently, deep learning has been leveraged to automatically generate layouts via image generation, showing a huge potential to free designers from laborious routines.  ...  To this end, we propose a new human-in-the-loop generative model, iPLAN, which is capable of automatically generating layouts, but also interacting with designers throughout the whole procedure, enabling  ...  Another related field is image composition from scene graphs, where the task is to derive the scene from a layout graph that describes the locations and features of the objects.  ... 
arXiv:2203.14412v1 fatcat:vpkcoqta3fgxjpttljcw766lva

Generative Layout Modeling using Constraint Graphs [article]

Wamiq Para, Paul Guerrero, Tom Kelly, Leonidas Guibas, Peter Wonka
2020 arXiv   pre-print
We propose a new generative model for layout generation. We generate layouts in three steps. First, we generate the layout elements as nodes in a layout graph.  ...  Second, we compute constraints between layout elements as edges in the layout graph. Third, we solve for the final layout using constrained optimization.  ...  is essential to make the floorplan look more realistic, but that is not learned from data.  ... 
arXiv:2011.13417v1 fatcat:ygmrjrqnafeqnd4hjidoehdcce

D2.1 Initial version of parametric design space

Antonios Liapis, Konstantinos Sfikas, Theodore Galanos, Georgios N. Yannakakis, Helmut Kinzler, Daria Zolotareva, Risa Tadauchi, Aleksandra Mnich-Spraiter, Jeg Dudley, Edoardo Tibuzzi, Arun Selvaraj, Dinos Ipiotis (+1 others)
2021 Zenodo  
This document takes input from the user and functional requirements of PrismArch described in D1.1 ("Report on current limitations of AEC software tools, leading to user and functional requirements of  ...  The final relevant deep learning approach for generating layouts at the pixel level is Graph2Plan [40] .  ...  of a floorplan from a connectivity graph through deep learning [40] or constrained programming [25] .  ... 
doi:10.5281/zenodo.5095065 fatcat:rtyb2l5qwbb7nfhwelonbgvgue

A Theory of L-shaped Floor-plans [article]

Raveena, Krishnendra Shekhawat
2022 arXiv   pre-print
Existing graph theoretic approaches are mainly restricted to floor-plans with rectangular boundary.  ...  Further, we present necessary and sufficient conditions for the existence of a non-trivial L-shaped floor-plan corresponding to a properly triangulated planar graph (PTPG) G.  ...  [RZY + 20] introduced deep neural network graph2plan approach for automated floor-plan generation from layout graphs.  ... 
arXiv:2205.14434v1 fatcat:ti45slx5yvbe7es2quwjde6dey