# LiftFormer: 3D Human Pose Estimation using attention models

arXiv: https://arxiv.org/abs/2009.00348 · HTML: https://mlsanity.com/paper/2009.00348/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation](https://mlsanity.com/paper/2110.05132/) (2021)
- [FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction](https://mlsanity.com/paper/2105.01937/) (2021)
- [Transforming Gait: Video-Based Spatiotemporal Gait Analysis](https://mlsanity.com/paper/2203.09371/) (2022)
- [UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues](https://mlsanity.com/paper/2404.14634/) (2024)
- [PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound](https://mlsanity.com/paper/2112.00216/) (2021)
- [Integrated In-vehicle Monitoring System Using 3D Human Pose Estimation and Seat Belt Segmentation](https://mlsanity.com/paper/2204.07946/) (2022)

## Abstract (arXiv)

Estimating the 3D position of human joints has become a widely researched topic in the last years. Special emphasis has gone into defining novel methods that extrapolate 2-dimensional data (keypoints) into 3D, namely predicting the root-relative coordinates of joints associated to human skeletons. The latest research trends have proven that the Transformer Encoder blocks aggregate temporal information significantly better than previous approaches. Thus, we propose the usage of these models to obtain more accurate 3D predictions by leveraging temporal information using attention mechanisms on ordered sequences human poses in videos. Our method consistently outperforms the previous best results from the literature when using both 2D keypoint predictors by 0.3 mm (44.8 MPJPE, 0.7% improvement) and ground truth inputs by 2mm (MPJPE: 31.9, 8.4% improvement) on Human3.6M. It also achieves state-of-the-art performance on the HumanEva-I dataset with 10.5 P-MPJPE (22.2% reduction). The number of parameters in our model is easily tunable and is smaller (9.5M) than current methodologies (16.95M and 11.25M) whilst still having better performance. Thus, our 3D lifting model's accuracy exceeds that of other end-to-end or SMPL approaches and is comparable to many multi-view methods.