Geometric Abstraction from Noisy Image-Based 3D Reconstructions.

Creating geometric abstracted models from image-based scene reconstructions is dicult due to noise and irregularities in the reconstructed model. In this paper, we present a geometric modeling method for noisy reconstructions dominated by planar horizontal and or- thogonal vertical structures. We partition the scene into horizontal slices and create an inside/outside labeling represented by a floor plan for each slice by solving an energy minimization problem. Consecutively, we cre- ate an irregular discretization of the volume according to the individual floor plans and again label each cell as inside/outside by minimizing an energy function. By adjusting the smoothness parameter, we introduce dierent levels of detail. In our experiments, we show results with varying regularization levels using synthetically generated and real-world data.