Flat2Layout: Flat Representation for Estimating Layout of General Room Types
This enables more accurate layout estimation for general indoor scenes, benefiting applications in scene modeling, robotics, and augmented reality.
The paper tackles the problem of estimating indoor room layouts from single-view RGB images, which existing methods could only do for box-shaped rooms, and achieves state-of-the-art performance on benchmarks, including a new one for general room types.
This paper proposes a new approach, Flat2Layout, for estimating general indoor room layout from a single-view RGB image whereas existing methods can only produce layout topologies captured from the box-shaped room. The proposed flat representation encodes the layout information into row vectors which are treated as the training target of the deep model. A dynamic programming based postprocessing is employed to decode the estimated flat output from the deep model into the final room layout. Flat2Layout achieves state-of-the-art performance on existing room layout benchmark. This paper also constructs a benchmark for validating the performance on general layout topologies, where Flat2Layout achieves good performance on general room types. Flat2Layout is applicable on more scenario for layout estimation and would have an impact on applications of Scene Modeling, Robotics, and Augmented Reality.