Data-driven interior plan generation for residential buildings
By Wenming Wu, Xiaoming Fu, Rui Tang, Yuhan Wang, Yuanhang Qi, Ligang Liu. ACM Transactions on Graphics, 2019
352 citations recorded by the source corpus.
We propose a novel data-driven technique for automatically and efficiently generating floor plans for residential buildings with given boundaries. Central to this method is a two-stage approach that imitates the human design process by locating rooms first and then walls while adapting to the input building boundary. Based on observations of the presence of the living room in almost all floor plans, our designed learning network begins with positioning a living room and continues by iteratively generating other rooms. Then, walls are first determined by an encoder-decoder network, and then they are refined to vector representations using dedicated rules. To effectively train our networks, we construct RPLAN - a manually collected large-scale densely annotated dataset of floor plans from real residential buildings. Intensive experiments, including formative user studies and comparisons, are conducted to illustrate the feasibility and efficacy of our proposed approach. By comparing the plausibility of different floor plans, we have observed that our method substantially outperforms existing methods, and in many cases our floor plans are comparable to human-created ones.
Subfields: Computer Vision and Pattern Recognition, Geology
View Paper: https://www.semanticscholar.org/paper/f04f828c1888ea968fad7af2259217b04d209fbe
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Roozbeh Mottaghi
- Aniruddha Kembhavi
- Ali Farhadi
- Kristen Grauman
- Luc Van Gool
- Jitendra Malik
- Abhinav Kumar Gupta
- Li Fei-Fei
In Geology
Citations in the corpus
- ProcTHOR: Large-Scale Embodied AI Using Procedural Generation (2022, methodology): “In this work, we found the procedural generation approaches to be more reliable and flexible than the ones based on deep learning when adapting it to our custom object database and when generating more complex houses that were out of the distribution of static house datasets [18, 57, 34].”
- Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI (2021, neutral): “Floorplan datasets [21–23] can be converted to 3D floorplans outlining the architectural layout of buildings and rooms using heuristics.”
- House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation (2020, background): “[25], and outdoor scene generation by Jyothi et al.”