The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry
Open accessAbstract
Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect. Various weakly or self supervised pose estimation methods have been proposed due to lack of 3D data. Nevertheless, these methods, in addition to 2D ground-truth poses, require either additional supervision in various forms (e.g. unpaired 3D ground truth data, a small subset of labels) or the camera parameters in multiview settings. To address these problems, we present EpipolarPose, a self-supervised learning method for 3D human pose estimation, which does not need any 3D ground-truth data or camera extrinsics. During training, EpipolarPose estimates 2D poses from multi-view images, and then, utilizes epipolar geometry to obtain a 3D pose and camera geometry which are subsequently used to train a 3D pose estimator. We demonstrate the effectiveness of our approach on standard benchmark datasets (i.e. Human3.6M and MPI-INF-3DHP) where we set the new state-of-the-art among weakly/self-supervised methods. Furthermore, we propose a new performance measure Pose Structure Score (PSS) which is a scale invariant, structure aware measure to evaluate the structural plausibility of a pose with respect to its ground truth. Code and pretrained models are available at https://github.com/mkocabas/EpipolarPose.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
(2017) · Cited by 11,625
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.143 · Cited by 7,539 · cited 1×
“Most recent methods in this category use state-of-the-art 2D pose estimators [7, 44, 25, 18] to obtain joint locations in the image plane.”
MethodStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
Ionescu, C., Papava, D., Olaru, V., & Sminchisescu, C. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.248 · Cited by 3,653 · cited 3×
“6M [15] and MPI-INF-3DHP [23] datasets, we set the new state-of-the-art in 3D pose estimation for weakly/self-supervised methods.”
BackgroundMethodWei, S.-E., Ramakrishna, V., Kanade, T., & Sheikh, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.511 · Cited by 2,966
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
Andriluka, M., Pishchulin, L., Gehler, P., & Schiele, B. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.471 · Cited by 2,688
An efficient solution to the five-point relative pose problem
Nister, D. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.17 · Cited by 2,009
A Simple Yet Effective Baseline for 3d Human Pose Estimation
Martinez, J., Hossain, R., Romero, J., & Little, J. J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.288 · Cited by 1,462
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision
Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., & Theobalt, C. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00064 · Cited by 1,142
Hartley, R. I., & Sturm, P. (1997) · Computer Vision and Image Understanding · doi:10.1006/cviu.1997.0547 · Cited by 961
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Pavlakos, G., Zhou, X., Derpanis, K. G., & Daniilidis, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.139 · Cited by 884
Integral Human Pose Regression
Sun, X., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_33 · Cited by 874
Deep Convolutional Inverse Graphics Network
Kulkarni, T. D., Whitney, W., Kohli, P., & Tenenbaum, J. B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.03167 · Cited by 653
3D Human Pose Estimation = 2D Pose Estimation + Matching
Chen, C.-H., & Ramanan, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.610 · Cited by 566
Compositional Human Pose Regression
Sun, X., Shang, J., Liang, S., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.284 · Cited by 542
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
Tome, D., Russell, C., & Agapito, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.603 · Cited by 504
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network
Li, S., & Chan, A. B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-16808-1_23 · Cited by 443
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
Zhou, X., Zhu, M., Leonardos, S., Derpanis, K. G., & Daniilidis, K. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.537 · Cited by 413
Ordinal Depth Supervision for 3D Human Pose Estimation
Pavlakos, G., Zhou, X., & Daniilidis, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00763 · Cited by 411
3D Human Pose Estimation from a Single Image via Distance Matrix Regression
Moreno-Noguer, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.170 · Cited by 397
Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation
Fang, H.-S., Xu, Y., Wang, W., Liu, X., & Zhu, S.-C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12270 · Cited by 332
MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network
Kocabas, M., Karagoz, S., & Akbas, E. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_26 · Cited by 314
Self-citationLCR-Net: Localization-Classification-Regression for Human Pose
Rogez, G., Weinzaepfel, P., & Schmid, C. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.134 · Cited by 296
3D Pictorial Structures for Multiple Human Pose Estimation
Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., & Ilic, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.216 · Cited by 258
Learning Monocular 3D Human Pose Estimation from Multi-view Images
Rhodin, H., Meyer, F., Sporri, J., Muller, E., Constantin, V., Fua, P., Katircioglu, I., & Salzmann, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00880 · Cited by 249
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
Tekin, B., Marquez-Neila, P., Salzmann, M., & Fua, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.425 · Cited by 242
Single Image 3D Interpreter Network
Tian, Y., Wu, J., Xue, T., Lim, J. J., Tenenbaum, J. B., Torralba, A. B., & Freeman, W. T. (2016) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 241
Structured Prediction of 3D Human Pose with Deep Neural Networks
Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., & Fua, P. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.130 · Cited by 236
Harvesting Multiple Views for Marker-Less 3D Human Pose Annotations
Pavlakos, G., Zhou, X., Derpanis, K. G., & Daniilidis, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.138 · Cited by 192
Discovery of Latent 3D Keypoints via End-to-end Geometric ReasoningPreprint
Suwajanakorn, S., Snavely, N., Tompson, J., & Norouzi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.03146 · Cited by 190
Multi-band Polarization Imaging and Applications
Zhao, Y., Yi, C., Kong, S. G., Pan, Q., & Cheng, Y. (2016) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-662-49373-1 · Cited by 180
3D Pictorial Structures for Multiple View Articulated Pose Estimation
Burenius, M., Sullivan, J., & Carlsson, S. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.464 · Cited by 158
Tung, H.-Y. F., Harley, A. W., Seto, W., & Fragkiadaki, K. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.467 · Cited by 143
Multi-view Pictorial Structures for 3D Human Pose Estimation
Amin, S., Andriluka, M., Rohrbach, M., & Schiele, B. (2013) · British Machine Vision Conference (BMVC) · doi:10.5244/c.27.45 · Cited by 142
3D Pictorial Structures Revisited: Multiple Human Pose Estimation
Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., & Ilić, S. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2509986 · Cited by 132
A Study of Parts-Based Object Class Detection Using Complete Graphs
Bergtholdt, M., Kappes, J. H., Schmidt, S., & Schnörr, C. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0209-1 · Cited by 130
Monocular 3D Human Pose Estimation by Predicting Depth on Joints
Nie, B. X., Wei, P., & Zhu, S. C. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.373 · Cited by 126
Can 3D Pose Be Learned from 2D Projections Alone?
Drover, D., Rohith, M. V., Chen, C.-H., Agrawal, A., Tyagi, A., & Huynh, C. P. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11018-5_7 · Cited by 111
How Robust is 3D Human Pose Estimation to Occlusion?Preprint
Sárándi, I., Linder, T., Arras, K. O., & Leibe, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.09316 · Cited by 91
MARCOnI—ConvNet-Based MARker-Less Motion Capture in Outdoor and Indoor Scenes
Elhayek, A., de Aguiar, E., Jain, A., Thompson, J., Pishchulin, L., Andriluka, M., Bregler, C., Schiele, B., & Theobalt, C. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2557779 · Cited by 71
Bayesian Image Based 3D Pose Estimation
Sanzari, M., Ntouskos, V., & Pirri, F. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_34 · Cited by 62
Cited by
VIBE: Video Inference for Human Body Pose and Shape Estimation
Kocabas, M., Athanasiou, N., & Black, M. J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00530 · Cited by 1,031
Self-citationDeep 3D human pose estimation: A review
Wang, J., Tan, S., Zhen, X., Xu, S., Zheng, F., He, Z., & Shao, L. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103225 · Cited by 399
Self-Supervised ECG Representation Learning for Emotion Recognition
Sarkar, P., & Etemad, A. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3014842 · Cited by 383
Anatomy-Aware 3D Human Pose Estimation With Bone-Based Pose Decomposition
Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., & Luo, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3057267 · Cited by 338
Exploiting Temporal Contexts With Strided Transformer for 3D Human Pose Estimation
Li, W., Liu, H., Ding, R., Liu, M., Wang, P., & Yang, W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3141231 · Cited by 314
Metadata
- Authors
- Kocabas, M., Karagoz, S., & Akbas, E.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 1077-1086
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2919066845
- Cited by
- 293
- References
- 45
- FWCI
- 15.77
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.