Browse > Article
http://dx.doi.org/10.3745/KTSDE.2022.11.12.509

Predicting Unseen Object Pose with an Adaptive Depth Estimator  

Sungho, Song (경기대학교 컴퓨터과학과)
Incheol, Kim (경기대학교 컴퓨터공학부)
Publication Information
KIPS Transactions on Software and Data Engineering / v.11, no.12, 2022 , pp. 509-516 More about this Journal
Abstract
Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.
Keywords
3D Vision; Unknown Object; 6D Pose Prediction; Depth Estimation; Deep Neural Network;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 C. Wang, D. Xu, Y. Zhu, R. Martin-Martin, C. Lu, L. Fei-Fei, and S. Savarese, "DenseFusion: 6D object pose estimation by iterative dense fusion," Proceedings of IEEE Computer Vision and Pattern Conference, 2019.
2 Z. He, W. Feng, X. Zhao, and Y. Lv, "6D Pose prediction of objects: Recent technologies and challenges," Applied Science, Vol.11, No.1, pp.228, 2021.
3 K. Park, A. Mousavian, Y. Xiang, and D. Fox, "LatentFusion: End-to-End differentiable reconstruction and rendering for unseen object pose prediction," Proceedings of IEEE Computer Vision and Pattern Conference, 2019.
4 E. Sucar, K. Wada, and A. Davison, "NodeSLAM: Neural object descriptors for multi-view shape reconstruction," Proceedings of 2020 International Conference on 3D Vision (3DV), 2020.
5 X. Chen, Z. Dong, J. Song, A. Geiger, and O. Hilliges, "Category level object pose estimation via neural analysis-by-synthesis," Proceedings of European Conference on Computer Vision, 2020.
6 D. Eigen, C. Puhrsch, and R. Fergus, "Depth map prediction from a single image using a multi-scale deep network," Proceedings of NeurIPS, 2014.
7 I. Alhashim, and P. Wonka. "High quality monocular depth estimation via transfer learning," arXiv preprint arXiv: 1812.1194, 2018.
8 L. Huynh, P. Nguyen-Ha, J. Matas, E. Rahtu, and J. Heikkila, "Guiding monocular depth estimation using depthattention volume." Proceedings of European Conference on Computer Vision, 2020.
9 I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari, and N. Navab, "Deeper depth prediction with fully convolutional residual networks," Proceedings of 2016 Fourth International Conference on 3D Vision (3DV), 2016.
10 J. Lee, M. Han, D. Ko, and I. Suh, "From big to small: Multi-scale local planar guidance for monocular depth estimation," arXiv preprint arXiv:/1907.10326, 2019.
11 T. Zhou, M. Brown, N. Snavely, and D. Lowe, "Unsupervised learning of depth and ego-motion from video," Proceedings of IEEE Computer Vision and Pattern Conference, 2017.
12 Z. Yin and J. Shi, "Geonet: Unsupervised learning of dense depth, optical flow and camera pose," Proceedings of IEEE Computer Vision and Pattern Conference, 2018.
13 S. F. Bhat, I. Alhashim, and P. Wonka, "AdaBins: Depth estimation using adaptive bins," Proceedings of IEEE Computer Vision and Pattern Conference, 2021.
14 H. Wang, S. Sridhar, J. Huang, J. Valentin, S. Song, and L. J. Guibas, "Normalized object coordinate space for category-level 6D object pose and size estimation," Proceedings of IEEE Computer Vision and Pattern Conference, 2019.
15 M. Tian, M. H. Ang Jr, and G. H. Lee, "Shape prior deformation for categorical 6D object pose and size estimation," Proceedings of European Conference on Computer Vision, 2020.
16 C. Lee, D. Shim, and H. Kim, "Deep learning based monocular depth estimation: Survey," Journal of Positioning Navigation and Timing, Vol.10, No.4, pp.297-305, 2021.
17 B. Tekin, S. N. Sinha, and P. Fua, "Real-time seamless single shot 6d object pose prediction," Proceedings of IEEE Computer Vision and Pattern Conference, 2018.
18 J. Tremblay, T. To, B. Sundaralingam, Y. Xiang, D. Fox, and S. Birchfield, "Deep object pose estimation for semantic robotic grasping of household objects," Proceedings of Conference Robot Learning, 2018.
19 Y. Li, G. Wang, X. Ji, Y. Xiang, and D. Fox, "DeepIM: Deep iterative matching for 6d pose prediction," Proceedings of European Conference on Computer Vision, 2018.
20 F. Manhardt, W. Kehl, N. Navab, and F. Tombari, "Deep model-based 6D pose refinement in RGB," Proceedings of European Conference on Computer Vision, 2018.
21 C. Li, J. Bai, and G. D. Hager, "A unified framework for multi-view multi-class object pose estimation," Proceedings of European Conference on Computer Vision, 2018.
22 J. Bian, H. Zhan, N. Wang, T. Chin, C. Shen, and I. Reid, "Auto-Rectify network for unsupervised indoor depth estimation," Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
23 B. Li, Y. Huang, Z. Liu, D. Zou, and W. Yu, "StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation," Proceedings of IEEE International Conference on Coputer Vision, 2021.
24 W. Yin, Y. Liu, and C. Shen, "Virtual Normal: Enforcing geometric constraints for accurate and robust depth prediction," Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.