RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View
This addresses the challenge of accurate room layout estimation for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of estimating non-cuboidal room layouts from single images by learning a ranking function instead of using optimization, achieving state-of-the-art results on standard datasets and performing well on non-cuboidal layouts.
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.