Automatic Environment Map Registration

Abstract

In this paper, a method to automatically register an environment map (EM) around a local scene is presented. In the literature, this step is most of the time manually processed by a user. However, it is an essential step when lighting and/or background coherence is needed. We present a method to find the coherent spatial organization between a main light source present in the EM and a couple object/shadow in a local scene. We automatically recover the EM orientation which corresponds to the local scene illumination. We proceed to a 3D representation of the scene using the EM mapped on a hemisphere as a background scene, a simplified geometry description of the reference object and its shadow outline. As a first step, we compute a projection of the main object shadow to compare it against the real acquired shadow. In a second step, we minimize a metric based on Euclidean Distance Transform (EDT), to compare both shadows and to recover the EM orientation. We demonstrate that we can automatically find rotation and scaling parameters that position in a coherent manner the background around a local scene.