Unit Region Encoding: A Unified and Compact Geometry-aware Representation for Floorplan Applications
This work addresses the need for a unified and compact representation in floorplan applications, offering incremental improvements over prior approaches.
The paper tackles the problem of representing floorplans for applications like interior planning and generation by introducing Unit Region Encoding, a geometry-aware encoding that uses boundary-adaptive unit regions based on a density map, achieving higher accuracy and better visual quality compared to existing methods.
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to floorplan generation tasks. The floorplans are represented as the latent encodings on a set of boundary-adaptive unit region partition based on the clustering of the proposed geometry-aware density map. The latent encodings are extracted by a trained network (URE-Net) from the input dense density map and other available semantic maps. Compared to the over-segmented rasterized images and the room-level graph structures, our representation can be flexibly adapted to different applications with the sliced unit regions while achieving higher accuracy performance and better visual quality. We conduct a variety of experiments and compare to the state-of-the-art methods on the aforementioned applications to validate the superiority of our representation, as well as extensive ablation studies to demonstrate the effect of our slicing choices.