Self-training Room Layout Estimation via Geometry-aware Ray-casting
This work addresses the challenge of estimating room layouts in complex, unlabeled environments for applications like robotics or augmented reality, offering an incremental advance over existing methods.
The paper tackles the problem of room layout estimation on unseen scenes with unlabeled data by introducing a geometry-aware self-training framework, resulting in significant improvements in state-of-the-art layout models without human annotation.
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple estimates from different viewing positions, enabling the computation of reliable pseudo-labels for self-training. In particular, our ray-casting approach enforces multi-view consistency along all ray directions and prioritizes spatial proximity to the camera view for geometry reasoning. As a result, our geometry-aware pseudo-labels effectively handle complex room geometries and occluded walls without relying on assumptions such as Manhattan World or planar room walls. Evaluation on publicly available datasets, including synthetic and real-world scenarios, demonstrates significant improvements in current state-of-the-art layout models without using any human annotation.