Geometrically guided and confidence-based point cloud denoising

Abstract

The generation of photogrammetric point clouds from satellite images is often based on image correlation techniques. Correlation errors can arise for a wide variety of reasons: transient objects, homogeneous areas, shadows, and surface discontinuities. Therefore, a simple 3D Gaussian distribution at the point cloud level is not an appropriate model. In this paper, we propose a new point cloud denoising method integrated into the Multiview Stereo Pipeline CARS, dedicated to satellite imagery. Building upon bilateral filtering principles, our approach introduces a novel utilization of color information, confidence estimation and geometric constraints alongside point positions and normals. While the use of point color increases the level of detail, the addition of geometric constraints and confidence awareness guides processing towards a realistic solution. We propose an ablation study and compare our solution against a previously established bilateral filter with LiDAR data as ground truth.