RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View

TL;DR

RoomStructNet introduces a novel CNN-based ranking approach for estimating both cuboidal and non-cuboidal room layouts from a single image, outperforming existing methods on standard datasets.

Contribution

It proposes a new learning framework that replaces optimization with a ranking function and explicitly models non-cuboidal layouts using layout complexity parameters.

Findings

Achieves state-of-the-art results on cuboidal layout datasets.

Performs well on non-cuboidal room layout datasets.

Introduces a CNN training method with max-margin structure cost.

Abstract

In this paper, we present a new approach to estimate the layout of a room from its single image. While recent approaches for this task use robust features learnt from data, they resort to optimization for detecting the final layout. In addition to using learnt robust features, our approach learns an additional ranking function to estimate the final layout instead of using optimization. To learn this ranking function, we propose a framework to train a CNN using max-margin structure cost. Also, while most approaches aim at detecting cuboidal layouts, our approach detects non-cuboidal layouts for which we explicitly estimates layout complexity parameters. We use these parameters to propose layout candidates in a novel way. Our approach shows state-of-the-art results on standard datasets with mostly cuboidal layouts and also performs well on a dataset containing rooms with non-cuboidal layouts.