ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design

TL;DR

This paper introduces ActFloor-GAN, a two-stage, human-centric approach for automated residential floorplan design that synthesizes human-activity maps to guide high-quality, topologically reasonable room layouts, incorporating user interaction and preferences.

Contribution

The paper presents a novel two-stage framework combining human-activity map synthesis with a GAN-guided layout prediction, improving the plausibility and user controllability of generated floorplans.

Findings

Outperforms prior methods in predicting room types using human-activity maps.

Generated floorplans are topologically comparable to professionally designed ones.

Allows user manipulation of furniture and activity considerations in design process.

Abstract

We present a novel two-stage approach for automated floorplan design in residential buildings with a given exterior wall boundary. Our approach has the unique advantage of being human-centric, that is, the generated floorplans can be geometrically plausible, as well as topologically reasonable to enhance resident interaction with the environment. From the input boundary, we first synthesize a human-activity map that reflects both the spatial configuration and human-environment interaction in an architectural space. We propose to produce the human-activity map either automatically by a pre-trained generative adversarial network (GAN) model, or semi-automatically by synthesizing it with user manipulation of the furniture. Second, we feed the human-activity map into our deep framework ActFloor-GAN to guide a pixel-wise prediction of room types. We adopt a re-formulated cycle-consistency constraint in ActFloor-GAN to maximize the overall prediction performance, so that we can produce high-quality room layouts that are readily convertible to vectorized floorplans. Experimental results show several benefits of our approach. First, a quantitative comparison with prior methods shows superior performance of leveraging the human-activity map in predicting piecewise room types. Second, a subjective evaluation by architects shows that our results have compelling quality as professionally-designed floorplans and much better than those generated by existing methods in terms of the room layout topology. Last, our approach allows manipulating the furniture placement, considers the human activities in the environment, and enables the incorporation of user-design preferences.