SDF-based RGB-D Camera Tracking in Neural Scene Representations
This work addresses camera tracking for robotics or AR/VR applications, but it is incremental as it compares existing neural representations for a specific task.
The paper tackled the problem of 6D pose tracking for a moving RGB-D camera in neural scene representations, showing that using a signed distance field-based representation speeds up tracking and leads to more robust and accurate pose estimates under limited computation time.
We consider the problem of tracking the 6D pose of a moving RGB-D camera in a neural scene representation. Different such representations have recently emerged, and we investigate the suitability of them for the task of camera tracking. In particular, we propose to track an RGB-D camera using a signed distance field-based representation and show that compared to density-based representations, tracking can be sped up, which enables more robust and accurate pose estimates when computation time is limited.