Automatic interior layout with user-specified furniture

Abstract A new automatic layout scheme for interior furniture is presented. According to user-specified furniture, an empty room region is divided into several functional areas by use of conditional generative adversarial networks. Each type of functional area can contain some categories of particular furniture objects, while each category of furniture belongs to one or several types of functional areas. We design a data-driven approach to place the furniture in all the functional areas. We expound the learning process of the division of the functional areas for the case with the user-specified furniture constraint, including to improve the furniture vector, objective function, and training process. Experiments show the proposed layout scheme has advantages in performance and effect compared with existing methods.

[1]  Hervé Luga,et al.  Constraint-Based 3D-Object Layout using a Genetic Algorithm , 2003 .

[2]  Matthias Nießner,et al.  Activity-centric scene synthesis for functional 3D scene modeling , 2015, ACM Trans. Graph..

[3]  Rob Fergus,et al.  Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks , 2016, ArXiv.

[4]  Chi-Keung Tang,et al.  Make it home: automatic optimization of furniture arrangement , 2011, SIGGRAPH 2011.

[5]  Kari Anne Høier Kjølaas,et al.  Automatic furniture population of large architectural models , 2000 .

[6]  Vladlen Koltun,et al.  Computer-generated residential building layouts , 2010, SIGGRAPH 2010.

[7]  Yun Ling,et al.  Automatic Furniture Layout Based on Functional Area Division , 2019, 2019 International Conference on Cyberworlds (CW).

[8]  Kun Zhou,et al.  Automatic 3D Indoor Scene Updating with RGBD Cameras , 2014, Comput. Graph. Forum.

[9]  Frank Ching.  Interior Design Illustrated , 1987 .

[10]  Maureen Mitton,et al.  Residential Interior Design: A Guide to Planning Spaces , 2007 .

[11]  T. Igarashi,et al.  Plushie: an interactive design system for plush toys , 2007, ACM Trans. Graph..

[12]  Christopher J. Headleand,et al.  A Time-Line Approach for the Generation of Simulated Settlements , 2017, 2017 International Conference on Cyberworlds (CW).

[13]  Bin Zhou,et al.  Adaptive synthesis of indoor scenes via activity-associated object relation graphs , 2017, ACM Trans. Graph..

[14]  Angel X. Chang,et al.  Deep convolutional priors for indoor scene synthesis , 2018, ACM Trans. Graph..

[15]  Maneesh Agrawala,et al.  Interactive furniture layout using interior design guidelines , 2011, SIGGRAPH 2011.

[16]  Hui Jiang,et al.  Generating images with recurrent adversarial networks , 2016, ArXiv.

[17]  Vladimir G. Kim,et al.  ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling , 2017, ACM Trans. Graph..

[18]  Shi-Min Hu,et al.  Sketch2Scene: sketch-based co-retrieval and co-placement of 3D models , 2013, ACM Trans. Graph..

[19]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Daniel Cohen-Or,et al.  GRAINS , 2018, ACM Trans. Graph..