Offset-Guided Attention Network for Room-Level Aware Floor Plan Segmentation
This addresses a specific limitation in floor plan recognition for applications requiring consistent room-level predictions, representing an incremental improvement over prior methods.
The paper tackles the problem of inconsistent semantic predictions within rooms in floor plan segmentation by proposing an Offset-Guided Attention mechanism and a Feature Fusion Attention module to improve room-level semantic consistency. Experimental results show the approach outperforms existing methods both qualitatively and quantitatively.
Recognition of floor plans has been a challenging and popular task. Despite that many recent approaches have been proposed for this task, they typically fail to make the room-level unified prediction. Specifically, multiple semantic categories can be assigned in a single room, which seriously limits their visual quality and applicability. In this paper, we propose a novel approach to recognize the floor plan layouts with a newly proposed Offset-Guided Attention mechanism to improve the semantic consistency within a room. In addition, we present a Feature Fusion Attention module that leverages the channel-wise attention to encourage the consistency of the room, wall, and door predictions, further enhancing the room-level semantic consistency. Experimental results manifest our approach is able to improve the room-level semantic consistency and outperforms the existing works both qualitatively and quantitatively.