Skip to main content
SpringerLink
Log in

EFN6D: an efficient RGB-D fusion network for 6D pose estimation

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Precise 6DoF (6D) object pose estimation is an essential topic for many intelligent applications, for example, robot grasping, virtual reality, and autonomous driving. Lacking depth information, traditional pose estimators using only RGB cameras consistently predict bias 3D rotation and translation matrices. With the wide use of RGB-D cameras, we can directly capture both the depth for the object relative to the camera and the corresponding RGB image. Most existing methods concatenate these two data sources directly, which does not make full use of their complementary relationship. Therefore, we propose an efficient RGB-D fusion network for 6D pose estimation, called EFN6D, to exploit the 2D–3D feature more thoroughly. Instead of directly using the original single-channel depth map, we encode the depth information into a normal map and point cloud data. To effectively fuse the surface texture features and the geometric contour features of the object, we feed the RGB images and the normal map into two ResNets. Besides, the PSP modules and skip connections are used between the two ResNets, which not only enhances cross modal fusion performance of the network but also enhances the network’s capability in handling objects at different scales. Finally, the fused features obtained from these two ResNets and the point cloud features are densely fused point by point to further strengthen the fusion of 2D and 3D information at a per-pixel level. Experiments on the LINEMOD and YCB-Video datasets show that our EFN6D outperforms state-of-the-art methods by a large margin.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Aubry M, Maturana D, Efros AA, Russell BC, Sivic J (2014) Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of cad models. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3762–3769. https://doi.org/10.1109/cvpr.2014.487

  • Besl PJ, McKay ND (1992) Method for registration of 3-D shapes. In: Sensor fusion IV: control paradigms and data structures, vol 1611, p 586–606. https://doi.org/10.1117/12.57955

  • Bui M, Zakharov S, Albarqouni S, Ilic S, Navab N (2018) When regression meets manifold learning for object recognition and pose estimation. In: IEEE international conference on robotics and automation (ICRA), pp 6140–6146. https://doi.org/10.1109/ICRA.2018.8460654

  • Charles RQ, Su H, Kaichun M, Guibas LJ (2017) PointNet: deep learning on point sets for 3D classification and segmentation. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 652–660. https://doi.org/10.1109/CVPR.2017.16

  • Chen W, Duan J, Basevi H, Chang HJ, Leonardis A (2020) PointPoseNet: point pose network for robust 6d object pose estimation. In: IEEE winter conference on applications of computer vision (WACV), p 2813–2822. https://doi.org/10.1109/WACV45572.2020.9093272

  • Du G, Wang K, Lian S, Zhao K (2021) Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artif Intell Rev 54(3):1677–1734. https://doi.org/10.1007/s10462-020-09888-5

    Article  Google Scholar 

  • Eitel A, Springenberg JT, Spinello L, Riedmiller M, Burgard W (2015) Multimodal deep learning for robust RGB-D object recognition. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), p 681–687. https://doi.org/10.1109/iros.2015.7353446

  • Gao G, Lauri M, Wang Y, Hu X, Zhang J, Frintrop S (2020) 6d object pose regression via supervised learning on point clouds. In: IEEE international conference on robotics and automation (ICRA), p 3643–3649. https://doi.org/10.1109/ICRA40945.2020.9197461

  • Guo J, Xing X, Quan W, Yan D-M, Gu Q, Liu Y, Zhang X (2021) Efficient center voting for object detection and 6D pose estimation in 3D point cloud. IEEE Trans Image Process 30:5072–5084. https://doi.org/10.1109/TIP.2021.3078109

    Article  ADS  PubMed  Google Scholar 

  • Gupta S, Girshick R, Arbeláez P, Malik J (2014)Learning rich features from RGB-D images for object detection and segmentation. In: European conference on computer vision (ECCV), p 345–360. https://doi.org/10.1007/978-3-319-10584-0_23

  • Hagelskjær F, Buch AG (2020) Pointvotenet: accurate object detection and 6 DOF pose estimation in point clouds. In: IEEE international conference on image processing (ICIP), pp 2641–2645. https://doi.org/10.1109/ICIP40778.2020.9191119

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), p 770–778. https://doi.org/10.1109/CVPR.2016.90

  • Hinterstoisser S, Holzer S, Cagniart C, Ilic S, Konolige K, Navab N, Lepetit V (2011) Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: IEEE international conference on computer vision (ICCV), p 858–865. https://doi.org/10.1109/ICCV.2011.6126326

  • Hinterstoisser S, Lepetit V, Ilic S, Holzer S, Bradski G, Konolige K, Navab N (2012) Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Asian conference on computer vision (ACCV), pp 548–562. https://doi.org/10.1007/978-3-642-37331-2_42

  • Hodan T, Haluza P, Obdržálek Š, Matas J, Lourakis M, Zabulis X (2017) T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: IEEE winter conference on applications of computer vision (WACV), pp 880–888. https://doi.org/10.1109/WACV.2017.103

  • Hodaň T, Michel F, Brachmann E, Kehl W, Buch AG, Kraft D, Drost B, Vidal J, Ihrke S, Zabulis X, Sahin C, Manhardt F, Tombari F, Kim T-K, Matas J, Rother C (2018) Bop: benchmark for 6D object pose estimation. In: European conference on computer vision (ECCV), p 19–35. https://doi.org/10.1007/978-3-030-01249-6_2

  • Hoppe H, DeRose T, Duchamp T, McDonald J, Stuetzle W (1992) Surface reconstruction from unorganized points. In: Proceedings of the 19th annual conference on computer graphics and interactive techniques, pp 71–78. https://doi.org/10.1145/133994.134011

  • Hua W, Guo J, Wang Y, Xiong R (2020) 3D point-to-keypoint voting network for 6D pose estimation. In: 16th International conference on control, automation, robotics and vision (ICARCV), p 536–541. https://doi.org/10.1109/ICARCV50220.2020.9305322

  • Hu Y, Fua P, Wang W, Salzmann M (2020) Single-stage 6D object pose estimation. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 2927–2936. https://doi.org/10.1109/CVPR42600.2020.00300

  • Hu Y, Hugonot J, Fua P, Salzmann M (2019) Segmentation-driven 6D object pose estimation. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 3380–3389. https://doi.org/10.1109/CVPR.2019.00350

  • Kehl W, Manhardt F, Tombari F, Ilic S, Navab N (2017) SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: IEEE international conference on computer vision (ICCV), p 1530–1538. https://doi.org/10.1109/ICCV.2017.169

  • Kendall A, Grimes M, Cipolla R (2015) PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: IEEE international conference on computer vision (ICCV), p 2938–2946. https://doi.org/10.1109/ICCV.2015.336

  • Lepetit V, Moreno-Noguer F, Fua P (2009) Epnp: an accurate \(O(n)\) solution to the pnp problem. Int J Comput Vis 81(2):155–166. https://doi.org/10.1007/s11263-008-0152-6

    Article  Google Scholar 

  • Li C, Bai J, Hager GD (2018a) A unified framework for multi-view multi-class object pose estimation. In: European conference on computer vision (ECCV), p 263–281. https://doi.org/10.1007/978-3-030-01270-0_16

  • Li Y, Wang G, Ji X, Xiang Y, Fox D (2018b) DeepIM: deep iterative matching for 6D pose estimation. In: European conference on computer vision (ECCV), p 695–711. https://doi.org/10.1007/978-3-030-01231-1_42

  • Li Z, Wang G, Ji X (2019) CDPN: coordinates-based disentangled pose network for real-time RGB-based 6-DoF object pose estimation. In: IEEE/CVF international conference on computer vision (ICCV), p 7677–7686. https://doi.org/10.1109/ICCV.2019.00777

  • Li Q, Hu R, Xiao J, Wang Z, Chen Y (2020) Learning latent geometric consistency for 6D object pose estimation in heavily cluttered scenes. J Vis Commun Image Represent. https://doi.org/10.1016/j.jvcir.2020.102790

    Article  Google Scholar 

  • Li Y, Ma L, Zhong Z, Liu F, Chapman MA, Cao D, Li J (2021) Deep learning for LiDAR point clouds in autonomous driving: a review. IEEE Trans Neural Netw Learn Syst 32(8):3412–3432. https://doi.org/10.1109/TNNLS.2020.3015992

    Article  PubMed  Google Scholar 

  • Makhataeva Z, Varol HA (2020) Augmented reality for robotics: a review. Robotics 9(2):21. https://doi.org/10.3390/robotics9020021

    Article  Google Scholar 

  • Park K, Patten T, Vincze M (2019) Pix2pose: pixel-wise coordinate regression of objects for 6D pose estimation. In: IEEE/CVF international conference on computer vision (ICCV), pp 7667–7676. https://doi.org/10.1109/ICCV.2019.00776

  • Peng S, Liu Y, Huang Q, Zhou X, Bao H (2019) PVNet: pixel-wise voting network for 6dof pose estimation. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 4556–4565. https://doi.org/10.1109/CVPR.2019.00469

  • Qi CR, Su H, Nießner M, Dai A, Yan M, Guibas LJ (2016) Volumetric and multi-view CNNS for object classification on 3D data. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 5648–5656. https://doi.org/10.1109/cvpr.2016.609

  • Qi C. R, Yi L, Su H, Guibas LJ (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st international conference on neural information processing systems (NIPS), pp 5105–5114. https://doi.org/10.1109/cvpr.2017.16

  • Rad M, Lepetit V (2017) BB8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: IEEE international conference on computer vision (ICCV), p 3848–3856. https://doi.org/10.1109/ICCV.2017.413

  • Saadi L, Besbes B, Kramm S, Bensrhair A (2021) Optimizing RGB-D fusion for accurate 6D of pose estimation. IEEE Robot Autom Lett 6(2):2413–2420. https://doi.org/10.1109/LRA.2021.3061347

    Article  Google Scholar 

  • Shi Y, Huang J, Xu X, Zhang Y, Xu K (2021) StablePose: learning 6D object poses from geometrically stable patches. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 15222–15231. https://doi.org/10.1109/CVPR46437.2021.01497

  • Shin Y, Balasingham I (2017) Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification. In: 39th Annual international conference of the IEEE engineering in medicine and biology society (EMBC), p 3277–3280. https://doi.org/10.1109/embc.2017.8037556

  • Sock J, Kim KI, Sahin C, Kim TK (2018) Multi-task deep networks for depth-based 6D object pose and joint registration in crowd scenarios. In: Proceedings of of British machine vision conference (BMVC)

  • Song C, Song J, Huang Q (2020) HybridPose: 6D object pose estimation under hybrid representations. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 428–437. https://doi.org/10.1109/CVPR42600.2020.00051

  • Su Y, Rambach J, Minaskan N, Lesur P, Pagani A, Stricker D (2019) Deep multi-state object pose estimation for augmented reality assembly. In: IEEE international symposium on mixed and augmented reality adjunct (ISMAR-Adjunct), p 222–227. https://doi.org/10.1109/ISMAR-Adjunct.2019.00-42

  • Tekin B, Sinha SN, Fua P (2018) Real-time seamless single shot 6D object pose prediction. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 292–301. https://doi.org/10.1109/CVPR.2018.00038

  • Tian M, Pan L, Ang MH, Hee Lee G (2020) Robust 6D object pose estimation by learning RGB-D features. In: IEEE international conference on robotics and automation (ICRA), p 6218–6224. https://doi.org/10.1109/ICRA40945.2020.9197555

  • Tremblay J, To T, Sundaralingam B, Xiang Y, Fox D, Birchfield S (2018) Deep object pose estimation for semantic robotic grasping of household objects. In: Proceedings of the 2nd conference on robot learning, volume 87 of proceedings of machine learning research, p 306–316

  • Wang G, Manhardt F, Shao J, Ji X, Navab N, Tombari F (2020) Self6D: self-supervised monocular 6D object pose estimation. In: European conference on computer vision (ECCV), p 108–125. https://doi.org/10.1007/978-3-030-58452-8_7

  • Wang C, Xu D, Zhu Y, Martin-Martin R, Lu C, Fei-Fei L, Savarese S (2019) DenseFusion: 6D object pose estimation by iterative dense fusion. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 3338–3347. https://doi.org/10.1109/CVPR.2019.00346

  • Xiang Y, Schmidt T, Narayanan V, Fox D (2018) PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. In: Robotics: science and systems (RSS). https://doi.org/10.15607/rss.2018.xiv.019

  • Xu D, Anguelov D, Jain A (2018) PointFusion: deep sensor fusion for 3D bounding box estimation. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 244–253. https://doi.org/10.1109/CVPR.2018.00033

  • Yuan Y, Wan J, Wang Q (2016) Congested scene classification via efficient unsupervised feature learning and density estimation. Pattern Recognit 56:159–169. https://doi.org/10.1016/j.patcog.2016.03.020

    Article  ADS  Google Scholar 

  • Zakharov S, Shugurov I, Ilic S (2019) DPOD: 6D pose object detector and refiner. In: IEEE/CVF international conference on computer vision (ICCV), p 1941–1950. https://doi.org/10.1109/ICCV.2019.00203

  • Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: IEEE conference on computer vision and pattern recognition (CVPR), p 6230–6239. https://doi.org/10.1109/CVPR.2017.660

  • Zhou Y, Tuzel O (2018) VoxelNet: end-to-end learning for point cloud based 3D object detection. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR), p 4490–4499. https://doi.org/10.1109/CVPR.2018.00472

Download references

Acknowledgements

The work is supported by the following projects: National Natural Science Foundation of China (NSFC) Essential project, Nr.: U2033218, 61831018; NSFC Nr.: 61772328

Author information

Authors and Affiliations

  1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China

    Yaming Wang, Xiaoyan Jiang, Zhijun Fang, Xihe Qiu & Jue Chen

  2. i-SOMET Incorporated Association, Morioka, Iwate, Japan

    Hamido Fujita

  3. Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Hamido Fujita

  4. College of Mathematical Sciences, Harbin Engineering University, Harbin, 150001, China

    Hamido Fujita

Authors
  1. Yaming Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoyan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hamido Fujita
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhijun Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xihe Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jue Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xiaoyan Jiang or Zhijun Fang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Jiang, X., Fujita, H. et al. EFN6D: an efficient RGB-D fusion network for 6D pose estimation. J Ambient Intell Human Comput 15, 75–88 (2024). https://doi.org/10.1007/s12652-022-03874-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-022-03874-1

Keywords

Search

Navigation