Abstract
We describe a data-driven method for inferring the camera viewpoints given multiple images of an arbitrary object. This task is a core component of classic geometric pipelines such as SfM and SLAM, and also serves as a vital pre-processing requirement for contemporary neural approaches (e.g. NeRF) to object reconstruction and view synthesis. In contrast to existing correspondence-driven methods that do not perform well given sparse views, we propose a top-down prediction based approach for estimating camera viewpoints. Our key technical insight is the use of an energy-based formulation for representing distributions over relative camera rotations, thus allowing us to explicitly represent multiple camera modes arising from object symmetries or views. Leveraging these relative predictions, we jointly estimate a consistent set of camera rotations from multiple images. We show that our approach outperforms state-of-the-art SfM and SLAM methods given sparse images on both seen and unseen categories. Further, our probabilistic approach significantly outperforms directly regressing relative poses, suggesting that modeling multimodality is important for coherent joint reconstruction. We demonstrate that our system can be a stepping stone toward in-the-wild reconstruction from multi-view datasets. The project page with code and videos can be found at jasonyzhang.com/relpose.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balntas, V., Li, S., Prisacariu, V.: RelocNet: continuous metric learning relocalisation using neural nets. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 782–799. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_46
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_32
Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., et al.: Uncertainty-driven 6D pose estimation of objects and scenes from a single RGB image. In: CVPR (2016)
Bukschat, Y., Vetter, M.: EfficientPose: an efficient, accurate and scalable end-to-end 6D multi object pose estimation approach. arXiv:2011.04307 (2020)
Campos, C., Elvira, R., Gómez, J.J., Montiel, J.M.M., Tardós, J.D.: ORB-SLAM3: an accurate open-source library for visual visual-inertial and multi-map SLAM. T-RO 37(6), 1874–1890 (2021)
Carlone, L., Tron, R., Daniilidis, K., Dellaert, F.: Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization. ICRA (2015)
Chen, B., Chin, T.J., Klimavicius, M.: Occlusion-robust object pose estimation with holistic representation. In: WACV (2022)
Chen, K., Snavely, N., Makadia, A.: Wide-baseline relative camera pose estimation with directional learning. In: CVPR (2021)
Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: NeurIPS (2016)
Corona, E., Kundu, K., Fidler, S.: Pose estimation for objects with rotational symmetry. In: IROS (2018)
Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: MonoSLAM: real-time single camera SLAM. TPAMI 29(6), 1052–1067 (2007)
Deng, X., Mousavian, A., Xiang, Y., Xia, F., Bretl, T., Fox, D.: PoseRBPF: a rao-blackwellized particle filter for 6D object pose tracking. In: RSS (2019)
Deng, X., Xiang, Y., Mousavian, A., Eppner, C., Bretl, T., Fox, D.: Self-supervised 6D object pose estimation for robot manipulation. In: ICRA (2020)
DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: CVPR-W (2018)
Dusmanu, M., et al.: D2-Net: a trainable CNN for joint detection and description of local features. In: CVPR (2019)
Dusmanu, Mihai, Schönberger, Johannes L.., Pollefeys, Marc: Multi-view optimization of local feature geometry. In: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas, Frahm, Jan-Michael. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 670–686. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_39
Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. TPAMI (2018)
Furukawa, Y., Curless, B., Seitz, S.M., Szeliski, R.: Towards internet-scale multi-view stereo. In: CVPR (2010)
Gilitschenski, I., Sahoo, R., Schwarting, W., Amini, A., Karaman, S., Rus, D.: Deep orientation uncertainty learning based on a Bingham loss. In: ICLR (2019)
Goel, S., Gkioxari, G., Malik, J.: Differentiable stereopsis: meshes from multiple views using differentiable rendering. In: CVPR (2022)
Harris, C., Stephens, M.: A Combined corner and edge detector. In: Alvey Vision Conference (1988)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: RePOSE: fast 6D object pose refinement via deep texture rendering. In: ICCV (2021)
Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: ICCV (2017)
Kendall, A., Cipolla, R.: Modelling uncertainty in deep learning for camera relocalization. In: ICRA (2016)
Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: ICCV (2015)
Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: ICCV (2021)
Lindenberger, P., Sarlin, P.E., Larsson, V., Pollefeys, M.: Pixel-perfect structure-from-motion with featuremetric refinement. In: ICCV (2021)
Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. TPAMI 33(5), 978–994 (2010)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI (1981)
Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: CVPR (2018)
Manhardt, F., et al.: Explaining the ambiguity of object detection and 6D pose from visual data. In: ICCV (2019)
Melekhov, I., Ylioinas, J., Kannala, J., Rahtu, E.: Relative camera pose estimation using convolutional neural networks. In: ACIVS (2017)
Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24
Mohlin, D., Sullivan, J., Bianchi, G.: Probabilistic orientation estimation with matrix fisher distributions. In: NeurIPS (2020)
Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. T-RO 31(5), 1147–1163 (2015)
Mur-Artal, R., Tardós, J.D.: ORB-SLAM2: an open-source SLAM system for monocular stereo and RGB-D cameras. T-RO 33(5), 1255–1262 (2017)
Murphy, K.A., Esteves, C., Jampani, V., Ramalingam, S., Makadia, A.: Implicit-PDF: non-parametric representation of probability distributions on the rotation manifold. In: ICML (2021)
Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: DTAM: dense tracking and mapping in real-time. In: ICCV (2011)
Novotny, D., Larlus, D., Vedaldi, A.: Learning 3D object categories by looking around them. In: ICCV (2017)
Novotny, D., Ravi, N., Graham, B., Neverova, N., Vedaldi, A.: C3DPO: canonical 3D pose networks for non-rigid structure from motion. In: ICCV (2019)
Oberweger, M., Rad, M., Lepetit, V.: Making deep heatmaps robust to partial occlusions for 3D object pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 125–141. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_8
Okorn, B., Gu, Q., Hebert, M., Held, D.: ZePHyR: zero-shot pose hypothesis scoring. In: ICRA (2021)
Okorn, B., Xu, M., Hebert, M., Held, D.: Learning orientation distributions for object pose estimation. In: IROS (2020)
Pautrat, R., Larsson, V., Oswald, M.R., Pollefeys, M.: Online invariance selection for local feature descriptors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 707–724. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_42
Prokudin, S., Gehler, P., Nowozin, S.: Deep directional statistics: pose estimation with uncertainty quantification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 542–559. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_33
Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: ICCV (2021)
Revaud, J., De Souza, C., Humenberger, M., Weinzaepfel, P.: R2D2: reliable and repeatable detector and descriptor. In: NeurIPS (2019)
Rodrigues, O.: Des lois géométriques qui régissent les déplacements d’un système solide dans l’espace, et de la variation des coordonnées provenant de ces déplacements considérés indépendamment des causes qui peuvent les produire. Journal de Mathématiques Pures et Appliquées 5 (1840)
Rosinol, A., Abate, M., Chang, Y., Carlone, L.: Kimera: an open-source library for real-time metric-semantic localization and mapping. In: ICRA (2020)
Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: CVPR (2019)
Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)
Schönberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)
Schönberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501–518. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_31
Schops, T., Sattler, T., Pollefeys, M.: BAD SLAM: bundle adjusted direct RGB-D SLAM. In: CVPR (2019)
Simonyan, K., Vedaldi, A., Zisserman, A.: Learning local feature descriptors using convex optimisation. TPAMI 36(8), 1573–1585 (2014)
Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3D. In: SIGGRAPH. ACM (2006)
Song, C., Song, J., Huang, Q.: HybridPose: 6D object pose estimation under hybrid representations. In: CVPR (2020)
Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: CVPR (2018)
Sundermeyer, M., Marton, Z.-C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 712–729. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_43
Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)
Tang, C., Tan, P.: BA-Net: dense bundle adjustment network. In: ICLR (2019)
Teed, Z., Deng, J.: DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras. In: NeurIPS (2021)
Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: CVPR (2018)
Tola, E., Lepetit, V., Fua, P.: Daisy: an efficient dense descriptor applied to wide-baseline stereo. TPAMI 32(5), 815–830 (2009)
Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment–a modern synthesis. In: International Workshop on Vision Algorithms (1999)
Truong, P., Danelljan, M., Timofte, R.: GLU-Net: global-local universal network for dense flow and correspondences. In: CVPR (2020)
Ummenhofer, B., et al.: DeMoN: depth and motion network for learning monocular stereo. In: CVPR (2017)
Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-Net: learning of structure and motion from video. arXiv:1704.07804 (2017)
Wang, C., et al.: DenseFusion: 6D object pose estimation by iterative dense fusion. In: CVPR (2019)
Wang, Q., Zhou, X., Hariharan, B., Snavely, N.: Learning feature descriptors using camera pose supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 757–774. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_44
Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: ICRA (2017)
Wang, W., Hu, Y., Scherer, S.: TartanVO: a generalizable learning-based VO. In: CoRL (2020)
Wei, X., Zhang, Y., Li, Z., Fu, Y., Xue, X.: DeepSFM: structure from motion via deep bundle adjustment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 230–247. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_14
Wong, J.M., et al.: SegICP: integrated deep semantic segmentation and pose estimation. IROS (2017)
Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. In: RSS (2018)
Xiao, Y., Qiu, X., Langlois, P., Aubry, M., Marlet, R.: Pose from shape: deep pose estimation for arbitrary 3D objects. In: BMVC (2019)
Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467–483. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_28
Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)
Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., Kanazawa, A.: Perceiving 3D human-object spatial arrangements from a single image in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 34–51. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_3
Zhang, J.Y., Yang, G., Tulsiani, S., Ramanan, D.: NeRS: neural reflectance surfaces for sparse-view 3D reconstruction in the wild. In: NeurIPS (2021)
Zhang, R.: Making convolutional networks shift-invariant again. In: ICML (2019)
Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 851–868. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_50
Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)
Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR (2019)
Zubizarreta, J., Aguinaga, I., Montiel, J.M.M.: Direct sparse mapping. T-RO (2020)
Acknowledgements
We would like to thank Gengshan Yang, Jonathon Luiten, Brian Okorn, and Elliot Wu for helpful feedback and discussion. This work was supported in part by the NSF GFRP (Grant No. DGE1745016), Singapore DSTA, and CMU Argo AI Center for Autonomous Vehicle Research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J.Y., Ramanan, D., Tulsiani, S. (2022). RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13691. Springer, Cham. https://doi.org/10.1007/978-3-031-19821-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-19821-2_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19820-5
Online ISBN: 978-3-031-19821-2
eBook Packages: Computer ScienceComputer Science (R0)