Geometric Abstraction from Noisy Image-Based 3D Reconstructions

TL;DR

This paper introduces a method for creating geometric abstractions from noisy image-based 3D reconstructions by partitioning scenes into slices, labeling regions, and adjusting detail levels through energy minimization.

Contribution

The paper presents a novel approach for geometric abstraction that effectively handles noise and irregularities in scene reconstructions by combining slicing, labeling, and energy minimization techniques.

Findings

Effective abstraction of noisy reconstructions demonstrated

Adjustable detail levels via smoothness parameter

Successful results on synthetic and real-world data

Abstract

Creating geometric abstracted models from image-based scene reconstructions is difficult 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 orthogonal 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 create 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 different levels of detail. In our experiments, we show results with varying regularization levels using synthetically generated and real-world data.