HybridPose: 6D Object Pose Estimation Under Hybrid Representations

By Chen Song, Jiaru Song, Qi-Xing Huang. Computer Vision and Pattern Recognition, 2020

298 citations recorded by the source corpus.

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). Different intermediate representations used by HybridPose can all be predicted by the same simple neural network, and outliers in predicted intermediate representations are filtered by a robust regression module. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and is significantly more accurate. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 79.2%, representing a 67.4% improvement from the current state-of-the-art approach.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/1195fbeed30ebfb13432b9a85c131af299c1dd42

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Dacheng Tao
2. S. Maybank
3. Lin Gao
4. Binqiang Zhao
5. Huan Fu
6. Mingming Gong
7. Rongfei Jia

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Huan Fu
3. S. Maybank
4. Mingming Gong
5. Lin Gao
6. Binqiang Zhao
7. Rongfei Jia
8. Ling Shao

In Control and Systems Engineering

1. Dacheng Tao
2. Huan Fu
3. Mingming Gong

Citations in the corpus

• GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (2021, unknown): “HybridPose [39] extends PVNet by predicting edges and axes of symmetries at the same time.”
• 3D-FUTURE: 3D Furniture Shape with TextURE (2020, methodology): “Recentworks thus employ RGB-D sensors and deep learning to improve keypoints detection or directly predict 6DoF pose from images (Kehl et al. 2016; Brachmann et al. 2014; Bo et al. 2014; Hinterstoisser et al. 2012; Xiang et al. 2017; Peng et al. 2019; Song et al. 2020; Tekin et al. 2018; Rad and Lep”
• Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, unknown): “25 HybridPose [Song et al., 2020] 94.”