Conditionally accepted to ACM Transactions on Graphics (Proc.
We present an interactive furniture layout system that assists users
by suggesting furniture arrangements that are based on interior
design guidelines. Our system incorporates the layout guidelines
as terms in a density function and generates layout suggestions by
rapidly sampling the density function using
a hardware-accelerated Monte Carlo sampler. Our results demonstrate that the suggestion generation functionality measurably increases the quality of furniture arrangements produced
by participants with no prior training in interior design.
A high-quality version of the video can be downloaded for offline
(DivX, 127 MB).
Eighteen participants arranged furniture in ﬁve rooms, starting
from initial disorganized conﬁgurations (a–e). Layouts produced
with and without suggestions were evaluated through blind pairwise
comparisons by professional interior designers (bottom). Results for
(a–d) indicate a statistically signiﬁcant preference (p < 0.01) for
layouts produced with suggestions, according to a two-tailed independent
single sample t-test.
Layouts produced by participants without (left) and with suggestions (right). From top to bottom: Living room a, living room b,
game room, piano room, living and dining room (click to enlarge images).