Semantic Segmentation of Urban Textured Meshes Through Point Sampling
This addresses the problem of limited semantic segmentation methods for urban textured meshes, which is incremental as it adapts existing point cloud techniques to a specific domain.
The paper tackles semantic segmentation of urban textured meshes by sampling point clouds from meshes and applying point cloud segmentation algorithms, achieving state-of-the-art results with about 4 points improvement in OA and 18 points in mIoU on the SUM dataset.
Textured meshes are becoming an increasingly popular representation combining the 3D geometry and radiometry of real scenes. However, semantic segmentation algorithms for urban mesh have been little investigated and do not exploit all radiometric information. To address this problem, we adopt an approach consisting in sampling a point cloud from the textured mesh, then using a point cloud semantic segmentation algorithm on this cloud, and finally using the obtained semantic to segment the initial mesh. In this paper, we study the influence of different parameters such as the sampling method, the density of the extracted cloud, the features selected (color, normal, elevation) as well as the number of points used at each training period. Our result outperforms the state-of-the-art on the SUM dataset, earning about 4 points in OA and 18 points in mIoU.