Search papers, labs, and topics across Lattice.
PolyLayout introduces a novel approach to multi-room layout estimation by parameterizing room layouts as Manhattan 3D polygons and optimizing them jointly across multiple rooms. This method leverages a neural network to predict an optimization objective based on robust pre-trained visual features, allowing for improved generalization to new datasets and camera configurations. Experimental results demonstrate that PolyLayout significantly outperforms existing methods in accuracy and robustness, particularly through its adaptive polygon refinement and structural cue utilization across rooms.
Jointly optimizing multi-room layouts as Manhattan polygons leads to significant gains in accuracy and robustness, outperforming traditional independent room estimation methods.
Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poor generalization to new datasets or restrictive geometric assumptions of the room shape or camera configuration. Most also estimate rooms independently, failing to exploit shared building structure such as dominant directions, ground plane or ceiling height. We propose PolyLayout, a multi-room layout estimation method that parameterizes room layouts as Manhattan 3D polygons and optimizes them jointly across multiple rooms. The optimization objective is predicted by a neural network on top of robust pre-trained visual features and trained end-to-end with supervision only on output room layouts. At the same time, camera projection and polygon updates remain explicit and model-based. This separation between learned scoring and geometry improves generalization to new datasets and camera parameters. During optimization, PolyLayout adaptively refines the polygon topology through iterative wall split and merge operations while jointly utilizing structural cues across rooms. We introduce two new multi-view multi-room layout benchmarks by providing layout annotations to existing datasets, and experiments show that PolyLayout outperforms prior approaches, both in terms of accuracy and robustness. Project page: https://ghanning.github.io/PolyLayout
