Multi-Branch High-Dimensional Guided Transformer-Based 3D Human Posture Estimation
Source abstract
Abstract
The human pose paradigm is estimated using a transformer-based multi-branch multidimensional directed the three-dimensional (3D) method that takes into account self-occlusion, badly posedness, and a lack of depth data in the per-frame 3D posture estimation from two-dimensional (2D) mapping to 3D mapping. Firstly, by examining the relationship between the movements of different bones in the human body, four virtual skeletons are proposed to enhance the cyclic constraints of limb joints. Then, multiple parameters describing the skeleton are fused and projected into a high-dimensional space. Utilizing a multi-branch network, motion features between bones and overall motion features are extracted to mitigate the drift error in the estimation results. Furthermore, the estimated relative depth is projected into 3D space, and the error is calculated against real 3D data, forming a loss function along with the relative depth error. This article adopts the average joint pixel error as the primary performance metric. Compared to the benchmark approach, the estimation findings indicate an increase in average precision of 1.8 mm within the Human3.6M sample.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Human Pose and Action Recognition · Diabetic Foot Ulcer Assessment and Management · Hand Gesture Recognition Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (35)
Show source-provided references
1. 3D human pose estimation from monocular images with deep convolutional neural network
2. Coarse-to-fine volumetric prediction for single-image 3D human pose
3. Compositional human pose regression
4. Integral human pose regression
5. A simple yet effective baseline for 3D human pose estimation
6. 3D human pose estimation = 2D pose estimation + matching
7. Learning to fuse 2D and 3D image cues for monocular body pose estimation
8. 3D human pose estimation from a single image via distance matrix regression
9. Monocular 3D human pose estimation by predicting depth on joints
10. HEMlets pose: Learning part-centric heatmap triplets for accurate 3D human pose estimation
11. Human pose regression with residual log-likelihood estimation
12. SPGNet: Spatial projection guided 3D human pose estimation in low dimensional space
13. Motion projection consistency-based 3-D human pose estimation with virtual bones from monocular videos10.1109/TCDS.2022.3185146 ↗
14. Learning skeletal graph neural networks for hard 3D pose estimation
15. Optimizing network structure for 3D human pose estimation
16. Jointformer: Single-frame lifting transformer with error prediction and refinement for 3D human pose estimation
17. Enhanced 3D human pose estimation from videos by using attention-based neural network with dilated convolutions10.1007/s11263-021-01436-0 ↗
18. 3D human pose estimation with spatial and temporal transformers
19. MHFormer: Multi-hypothesis transformer for 3D human pose estimation
20. Exploiting temporal contexts with strided transformer for 3D human pose estimation10.1109/TMM.2022.3141231 ↗
21. Motion guided 3D pose estimation from videos
22. MixSTE: Seq2seq mixed spatio-temporal encoder for 3D human pose estimation in video
23. FLEX: Extrinsic parameters-free multi-view 3D human motion reconstruction
24. TransFusion: Cross-view fusion with transformer for 3D human pose estimation
25. Adaptive multi-view and temporal fusing transformer for 3D human pose estimation10.1109/TPAMI.2022.3188716 ↗
26. Attention is all you need
27. Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments10.1109/TPAMI.2013.248 ↗
28. 3D human pose estimation in video with temporal convolutions and semi-supervised training
29. Cascaded pyramid network for multi-person pose estimation
30. 3D human pose estimation in the wild by adversarial learning
31. A comprehensive study of weight sharing in graph networks for 3D human pose estimation
32. Graph stacked hourglass networks for 3D human pose estimation
33. Semantic graph convolutional networks for 3D human pose regression
34. 3D human pose estimation using möbius graph convolutional networks
35. Realtime multi-person 2D pose estimation using part affinity fields