Transferring facade labels between point clouds with semantic octrees while considering change detection
This work addresses the need for automatic label transfer in point clouds for fields like surveying and construction, but it appears incremental as it builds on existing octree-based methods with added change detection.
The paper tackles the problem of transferring semantic labels between labeled and unlabeled point clouds representing the same real-world object, using an octree structure that also analyzes changes, and reports that the method effectively transfers annotations while addressing changes.
Point clouds and high-resolution 3D data have become increasingly important in various fields, including surveying, construction, and virtual reality. However, simply having this data is not enough; to extract useful information, semantic labeling is crucial. In this context, we propose a method to transfer annotations from a labeled to an unlabeled point cloud using an octree structure. The structure also analyses changes between the point clouds. Our experiments confirm that our method effectively transfers annotations while addressing changes. The primary contribution of this project is the development of the method for automatic label transfer between two different point clouds that represent the same real-world object. The proposed method can be of great importance for data-driven deep learning algorithms as it can also allow circumventing stochastic transfer learning by deterministic label transfer between datasets depicting the same objects.