Coplanar Repeats by Energy Minimization

TL;DR

This paper introduces an energy minimization approach for automatic detection, grouping, and rectification of coplanar repeated elements in images, improving accuracy over existing methods.

Contribution

It presents a novel energy functional and an efficient inference framework for identifying and rectifying coplanar repeats in complex scenes.

Findings

Significant improvement in rectification accuracy compared to baseline methods.

Effective modeling of global interactions between scene planes and repeats.

Fast convergence of the proposed inference algorithm.

Abstract

This paper proposes an automated method to detect, group and rectify arbitrarily-arranged coplanar repeated elements via energy minimization. The proposed energy functional combines several features that model how planes with coplanar repeats are projected into images and captures global interactions between different coplanar repeat groups and scene planes. An inference framework based on a recent variant of $\alpha$-expansion is described and fast convergence is demonstrated. We compare the proposed method to two widely-used geometric multi-model fitting methods using a new dataset of annotated images containing multiple scene planes with coplanar repeats in varied arrangements. The evaluation shows a significant improvement in the accuracy of rectifications computed from coplanar repeats detected with the proposed method versus those detected with the baseline methods.