Better object pose and tracking by propagating keypoints with CenterPoseTrack
Better object pose and tracking by propagating keypoints with CenterPoseTrack
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
arXiv paper abstract https://arxiv.org/abs/2205.11047
arXiv PDF paper https://arxiv.org/pdf/2205.11047.pdf
Project page https://sites.google.com/view/centerposetrack
... propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category.
... takes as input the previous and current frame from a monocular RGB video, as well as predictions from the previous frame, to predict the bounding cuboid and 6-DoF pose
... deep network predicts distributions over object keypoints (vertices of the bounding cuboid) in image coordinates, after which a novel probabilistic filtering process integrates across estimates before computing the final pose using PnP.
... take previous uncertainties into consideration when predicting the current frame, resulting in predictions that are more accurate and stable than single frame methods.
... method outperforms existing approaches ... demonstrate the usability of ... work in ... augmented reality ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments