Rendering and Tracking the Directional TSDF: Modeling Surface Orientation for Coherent Maps
This work provides incremental improvements for robotic applications like navigation or grasping by enhancing map coherence and tracking performance.
The paper tackled the problem of dense real-time tracking and mapping from RGB-D images by extending the Directional Truncated Signed Distance Function (DTSDF) to render depth and color maps, making it a drop-in replacement for existing trackers. The result showed increased re-usability of mapped scenes and notably improved color-correctness at adjacent surfaces.
Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation or grasping. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF and shows potential for more coherent maps and improved tracking performance. In this work, we present methods for rendering depth- and color maps from the DTSDF, making it a true drop-in replacement for the regular TSDF in established trackers. We evaluate and show, that our method increases re-usability of mapped scenes. Furthermore, we add color integration which notably improves color-correctness at adjacent surfaces.