6-DoF Object Pose from Semantic Keypoints
arXiv:1703.04670
Abstract
This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior work, we are agnostic to whether the object is textured or textureless, as the convnet learns the optimal representation from the available training image data. Furthermore, the approach can be applied to instance- and class-based pose recovery. Empirically, we show that the proposed approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios with a cluttered background. For class-based object pose estimation, state-of-the-art accuracy is shown on the large-scale PASCAL3D+ dataset.
IEEE International Conference on Robotics and Automation (ICRA), 2017
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Manopt, a Matlab toolbox for optimization on manifolds
- Do Convnets Learn Correspondence?
- Convolutional Neural Networks for joint object detection and pose estimation: A comparative study
- Global Hypothesis Generation for 6D Object Pose Estimation
Cited by in corpus (13)
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
- DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
- Estimating 6D Pose From Localizing Designated Surface Keypoints
- 3D Bounding Box Estimation Using Deep Learning and Geometry
- 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
- 3D Pose Estimation for Fine-Grained Object Categories
- OrcVIO: Object residual constrained Visual-Inertial Odometry
- StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
- Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration
- Fast 3D Pose Refinement with RGB Images
- Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images
- Estimating Metric Poses of Dynamic Objects Using Monocular Visual-Inertial Fusion
- Improving drone localisation around wind turbines using monocular model-based tracking