Better understanding and modelling of building interiors and the emergence of more impressive AR/VR technology has brought up the need for automatic parsing of floorplan images. However, there is a clear lack of representative datasets to investigate the problem further. To address this shortcoming, this paper presents a novel image dataset called CubiCasa5K, a large-scale floorplan image dataset containing 5000 samples annotated into over 80 floorplan object categories. The dataset annotations are performed in a dense and versatile manner by using polygons for separating the different objects. Diverging from the classical approaches based on strong heuristics and low-level pixel operations, we present a method relying on an improved multi-task convolutional neural network. By releasing the novel dataset and our implementations, this study significantly boosts the research on automatic floorplan image analysis as it provides a richer set of tools for investigating the problem in a more comprehensive manner.

No abstract

No abstract

No abstract

In this paper we present the user evaluation results on the indication of interactive three dimensional elements in a virtual environment. The evaluation was conducted with a functional prototype and additional high quality images that were printed on paper sheets. The evaluation indicated that without any visual indication provided in the prototype, participants were not sure which items in the office scene are interactable when they enter to the scene. Also the indication while a user is interacting with the prototype, needs to be distinctive enough. For the visual indication of interactable elements in the virtual environment, participants preferred a glow effect in both circumstances; 1st while they enter to the virtual environment and 2nd while they are interacting with the elements. This information is useful to HCI researchers, 3D UI designers and developers to improve user experiences with virtual environments.