The DOI matches its Crossref record; 71 of the 71 references it cites were found in a registry or an index.
VIBE: Video Inference for Human Body Pose and Shape Estimation
Open accessAbstract
Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methods fail to produce accurate and natural motion sequences due to a lack of ground-truth 3D motion data for training. To address this problem, we propose "Video Inference for Body Pose and Shape Estimation'' (VIBE), which makes use of an existing large-scale motion capture dataset (AMASS) together with unpaired, in-the-wild, 2D keypoint annotations. Our key novelty is an adversarial learning framework that leverages AMASS to discriminate between real human motions and those produced by our temporal pose and shape regression networks. We define a novel temporal network architecture with a self-attention mechanism and show that adversarial training, at the sequence level, produces kinematically plausible motion sequences without in-the-wild ground-truth 3D labels. We perform extensive experimentation to analyze the importance of motion and demonstrate the effectiveness of VIBE on challenging 3D pose estimation datasets, achieving state-of-the-art performance. Code and pretrained models are available at https://github.com/mkocabas/VIBE
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 1×
“These are sent to a Gated Recurrent Unit (GRU) layer [13] that yields a latent feature vector gi for each frame, g(f1), .”
MethodImage-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“Generative adversarial networks GANs [5, 18, 27, 39] have had a signifi-cant impact on image modeling and synthesis.”
BackgroundAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665 · cited 1×
“We use a ResNet-50 network [22] as an image encoder pretrained on single frame pose and shape estimation task [29, 36] that outputs f i ∈ R 2048 .”
Method
Cited by
End-to-End Human Pose and Mesh Reconstruction with Transformers
Lin, K., Wang, L., & Liu, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00199 · Cited by 740
“…and shape coefficients directly from an input image, recent works further propose to leverage various human body priors such as human skeletons [26, 39] or segmentation maps [34], and explore different optimization strategies [24, 22, 51, 14] and temporal information [23] to improve reconstruction.”
BackgroundMethodInfluentialAgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting
Yuan, Y., Weng, X., Ou, Y., & Kitani, K. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00967 · Cited by 631
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
Li, R., Yang, S., Ross, D. A., & Kanazawa, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01315 · Cited by 553
“We use the 2D mean per joint position error MPJPE2D, commonly used for 3D reconstruction quality measurement [46, 39, 65]) to evaluate the consistency between the predicted 2D keypoints and the reconstructed 3D keypoints along with the estimated camera parameters.”
MethodAction-Conditioned 3D Human Motion Synthesis with Transformer VAE
Petrovich, M., Black, M. J., & Varol, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01080 · Cited by 493
Self-citationMotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2022) · arXiv · doi:10.48550/arxiv.2208.15001 · Cited by 437
Tretschk, E., Tewari, A., Golyanik, V., Zollhofer, M., Lassner, C., & Theobalt, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01272 · Cited by 432
MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3355414 · Cited by 424
PARE: Part Attention Regressor for 3D Human Body Estimation
Kocabas, M., Huang, C.-H. P., Hilliges, O., & Black, M. J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01094 · Cited by 417
Self-citationLi, J., Xu, C., Chen, Z., Bian, S., Yang, L., & Lu, C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00339 · Cited by 402
Deep 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
Executing your Commands via Motion Diffusion in Latent Space
Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., & Yu, G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01726 · Cited by 356
MotionBERT: A Unified Perspective on Learning Human Motion Representations
Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., & Wang, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01385 · Cited by 348
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
Zhang, H., Tian, Y., Zhou, X., Ouyang, W., Liu, Y., Wang, L., & Sun, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01125 · Cited by 341
Lin, K., Wang, L., & Liu, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01270 · Cited by 337
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction
Zheng, Z., Yu, T., Liu, Y., & Dai, Q. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3050505 · Cited by 320
ICON: Implicit Clothed humans Obtained from Normals
Xiu, Y., Yang, J., Tzionas, D., & Black, M. J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01294 · Cited by 318
Self-citationHuMoR: 3D Human Motion Model for Robust Pose Estimation
Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., & Guibas, L. J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01129 · Cited by 304
Illuminating the dark spaces of healthcare with ambient intelligence
Haque, A., Milstein, A., & Fei-Fei, L. (2020) · Nature · doi:10.1038/s41586-020-2669-y · Cited by 274
“168 ; federated learning, ref.”
Humans in 4D: Reconstructing and Tracking Humans with Transformers
Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., & Malik, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01358 · Cited by 272
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs
Rosinol, A., Violette, A., Abate, M., Hughes, N., Chang, Y., Shi, J., Gupta, A., & Carlone, L. (2021) · The International Journal of Robotics Research · doi:10.1177/02783649211056674 · Cited by 271
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
Li, Z., Liu, J., Zhang, Z., Xu, S., & Yan, Y. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20065-6_34 · Cited by 268
Gait Recognition in the Wild with Dense 3D Representations and A Benchmark
Zheng, J., Liu, X., Liu, W., He, L., Yan, C., & Mei, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01959 · Cited by 260
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
Choi, H., Moon, G., Chang, J. Y., & Lee, K. M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00200 · Cited by 254
Monocular, One-stage, Regression of Multiple 3D People
Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M. J., & Mei, T. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01099 · Cited by 254
Self-citationSTAR: Sparse Trained Articulated Human Body Regressor
Osman, A. A. A., Bolkart, T., & Black, M. J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_36 · Cited by 252
“This makes it useful to reason about 3D human body pose and shape given sparse measurements, such as IMU accelerations [11,12,26], sparse mocap markers [22,25] or 2D key points in images and videos [3,14,15,16,28,33,36,38].”
BackgroundSelf-citationTashakori, A., Jiang, Z., Servati, A., Soltanian, S., Narayana, H., Le, K., Nakayama, C., Yang, C.-L., Wang, Z. J., Eng, J. J., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-023-00780-9 · Cited by 137
Metadata
- Authors
- Kocabas, M., Athanasiou, N., & Black, M. J.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 5252-5262
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2995321487
- Cited by
- 1,031
- References
- 71
- FWCI
- 47.61
- 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.