Recent advances in scanning technologies, in particular devices that extract depth through active sensing, allow fast scanning of urban scenes. Such rapid acquisition incurs imperfections: large regions remain missing, significant variation in sampling density is common, and the data is often corrupted with noise and outliers. However, buildings often exhibit large scale repetitions and selfsimilarities. Detecting, extracting, and utilizing such large scale repetitions provide powerful means to consolidate the imperfect data. Our key observation is that the same geometry, when scanned multiple times over reoccurrences of instances, allow application of a simple yet effective non-local filtering. The multiplicity of the geometry is fused together and projected to a base-geometry defined by clustering corresponding surfaces. Denoising is applied by separating the process into off-plane and in-plane phases. We show that the consolidation of the reoccurrences provides robust denoising and allow reliable completion of missing parts. We present evaluation results of the algorithm on several LiDAR scans of buildings of varying complexity and styles. 1

Typical building facades consist of regular structures such as windows arranged in a predominantly grid-like manner. We propose a method that handles precisely such facades and assumes that there must be horizontal and vertical repetitions of similar patterns. Using a Monte Carlo sampling approach, this method is able to segment repetitive patterns on orthogonal images along the axes even if the pattern is partially occluded. Additionally, it is very fast and can be used as a preprocessing step for finer segmentation stages.

Figure 1: Steps of the proposed multi-view image generation system. Top-left: one of typical perspective input photographs, please note the occlusion. Top-middle: the result of the proposed ortho-image generation method (note the pedestrians). Second row shows masks indicating source images of the composition by colors: automatic result (left) and interactively post-processed (middle). Right: the final result after interactive post-processing. We propose a system for generating high-quality approximated façade ortho-textures based on a set of perspective source photographs taken by a consumer hand-held camera. Our approach is to sample a combined orthographic approximation over the façade-plane from the input photos. In order to avoid kinks and seams which may occur on transitions between different source images, we introduce color adjustment and gradient domain stitching by solving a Poisson equation in real-time. In order to add maximum control on the one hand and easy interaction on the other, we provide several editing interactions allowing for user-guided post-processing.