ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
Preprint
Abstract
Establishing correspondences from image to 3D has been a key task of 6DoF object pose estimation for a long time. To predict pose more accurately, deeply learned dense maps replaced sparse templates. Dense methods also improved pose estimation in the presence of occlusion. More recently researchers have shown improvements by learning object fragments as segmentation. In this work, we present a discrete descriptor, which can represent the object surface densely. By incorporating a hierarchical binary grouping, we can encode the object surface very efficiently. Moreover, we propose a coarse to fine training strategy, which enables fine-grained correspondence prediction. Finally, by matching predicted codes with object surface and using a PnP solver, we estimate the 6DoF pose. Results on the public LM-O and YCB-V datasets show major improvement over the state of the art w.r.t. ADD(-S) metric, even surpassing RGB-D based methods in some cases.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAMIEEE Transactions on Robotics, 2021
- SynPo-Net—Accurate and Fast CNN-Based 6DoF Object Pose Estimation Using Synthetic TrainingSensors, 2021
- Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation2018
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes2018
- A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies2018
- BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth2017
- Pose Estimation for Augmented Reality: A Hands-On SurveyIEEE Transactions on Visualization and Computer Graphics, 2015
- Gradient Response Maps for Real-Time Detection of Textureless ObjectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- The MOPED framework: Object recognition and pose estimation for manipulationThe International Journal of Robotics Research, 2011
- EPnP: An Accurate O(n) Solution to the PnP ProblemInternational Journal of Computer Vision, 2008