Rendering the Directional TSDF for Tracking and Multi-Sensor Registration with Point-To-Plane Scale ICP
This work addresses incremental improvements in tracking and mapping for robotic applications like navigation and manipulation.
The paper tackled the problem of dense real-time tracking and mapping from RGB-D images by rendering depth and color images from the Directional TSDF, making it a drop-in replacement for regular TSDF in trackers. The result showed improved tracking performance and increased re-usability of mapped scenes, with notable improvements in 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 and manipulation. The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF that shows potential for more coherent maps and improved tracking performance. In this work, we present methods for rendering depth- and color images from the DTSDF, making it a true drop-in replacement for the regular TSDF in established trackers. We evaluate the algorithm on well-established datasets and observe that our method improves tracking performance and increases re-usability of mapped scenes. Furthermore, we add color integration which notably improves color-correctness at adjacent surfaces. Our novel formulation of combined ICP with frame-to-keyframe photometric error minimization further improves tracking results. Lastly, we introduce Sim3 point-to-plane ICP for refining pose priors in a multi-sensor scenario with different scale factors.