AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
This addresses plane estimation for robotics and augmented reality applications, but is incremental as it builds on existing geometric methods with semantic enhancements.
The paper tackled the problem of estimating planar surfaces from posed images by proposing a method that predicts multi-view consistent plane embeddings to complement geometry, showing it outperforms existing approaches and a strong geometric baseline on the ScanNetV2 dataset.
Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene from posed images. Our first finding is that a surprisingly competitive baseline results from combining popular clustering algorithms with recent improvements in 3D geometry estimation. However, such purely geometric methods are understandably oblivious to plane semantics, which are crucial to discerning distinct planes. To overcome this limitation, we propose a method that predicts multi-view consistent plane embeddings that complement geometry when clustering points into planes. We show through extensive evaluation on the ScanNetV2 dataset that our new method outperforms existing approaches and our strong geometric baseline for the task of plane estimation.