Abstract

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 geom- etry 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 sce- narios, demonstrates significant improvements in current state-of-the-art layout models without using any human annotation.

Video

Citation

Acknowledgements

This project is supported by The National Science and Technology Council NSTC and The Taiwan Computing Cloud TWCC under the project NSTC 112- 2634-F-002-006. We also thanks to the Industrial Technology Research Institute ITRI, Taiwan.
The website template was borrowed from Michaël Gharbi.