Automatic Pose Recovery for High-Quality Textures Generation

Abstract

This paper proposes new techniques to generate high quality textures for urban building models by automatic camera calibration and pose recovery. The camera pose is decomposed into an orientation and a translation, an edge error model and knowledge-based filters are used to estimate correct vanishing points with heavy trees occlusion, and the vanishing points are used for the camera calibration and orientation estimation. We propose new techniques to estimate the camera orientation with infinite vanishing points and translation with under-constraints. The final textures are generated using color calibration and blending with the recovered pose. A number of textures for outdoor buildings are automatically generated, which shows the effectiveness of our algorithms.