Real-time texturing for 6D object instance detection from RGB Images

TL;DR

This paper introduces a real-time method for generating texture-maps from RGB image sequences to enhance 6D object detection, enabling on-the-fly detector improvement and object instance differentiation.

Contribution

It presents a novel real-time texturing approach that integrates detection and texturing, improving detection accuracy and object differentiation in RGB images.

Findings

Texture-maps significantly improve detection rates.

Method enables real-time detector upgrading.

Differentiates object instances by surface color.

Abstract

For objected detection, the availability of color cues strongly influences detection rates and is even a prerequisite for many methods. However, when training on synthetic CAD data, this information is not available. We therefore present a method for generating a texture-map from image sequences in real-time. The method relies on 6 degree-of-freedom poses and a 3D-model being available. In contrast to previous works this allows interleaving detection and texturing for upgrading the detector on-the-fly. Our evaluation shows that the acquired texture-map significantly improves detection rates using the LINEMOD detector on RGB images only. Additionally, we use the texture-map to differentiate instances of the same object by surface color.