| NIKI (Twist-and-Swing) |
- PA-MPJPE
- 40.6
- MPJPE
- 71.3
- MPVPE
- 86.6
|
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation 2023-05-15 |
코드 1 |
| HeatER |
- PA-MPJPE
- 45.9
- MPJPE
- 73.4
- MPVPE
- 86.9
|
FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER 2022-05-30 |
코드 1 |
| ImpHMR |
- PA-MPJPE
- 45.4
- MPJPE
- 74.3
- MPVPE
- 87.1
|
Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view 2023-06-30 |
연결 없음 |
| XFormer (HRNet) |
- PA-MPJPE
- 45.7
- MPJPE
- 75
- MPVPE
- 87.1
|
XFormer: Fast and Accurate Monocular 3D Body Capture 2023-05-18 |
연결 없음 |
| POTTER |
- PA-MPJPE
- 44.8
- MPJPE
- 75
- MPVPE
- 87.4
|
POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery 2023-03-23 |
코드 1 |
| INT-2 (ResNet-50) |
- PA-MPJPE
- 42
- MPJPE
- 75.6
- MPVPE
- 87.9
- Acceleration Error
- 16.5
|
Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens 2023-03-01 |
코드 1 |
| MotionBERT (Finetune) |
- PA-MPJPE
- 47.2
- MPJPE
- 76.9
- MPVPE
- 88.1
|
MotionBERT: A Unified Perspective on Learning Human Motion Representations 2022-10-12 |
코드 1 |
| BOA (w/ 2D GT) |
- PA-MPJPE
- 49.5
- MPJPE
- 77.2
- MPVPE
- 91.2
|
Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction 2021-03-30 |
코드 1 |
| SEFD |
- PA-MPJPE
- 49.39
- MPJPE
- 77.37
- MPVPE
- 92.60
|
SEFD: Learning to Distill Complex Pose and Occlusion 2023-01-01 |
코드 1 |
| DST-VIBE |
- PA-MPJPE
- 50.3
- MPJPE
- 76.7
- MPVPE
- 93.5
- Acceleration Error
- 11
|
Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation 2021-10-22 |
연결 없음 |
| LMR |
- PA-MPJPE
- 51.2
- MPJPE
- 81.7
- MPVPE
- 93.6
- Acceleration Error
- 15.6
|
Learning Local Recurrent Models for Human Mesh Recovery 2021-07-27 |
연결 없음 |
| GLoT |
- PA-MPJPE
- 50.6
- MPJPE
- 80.7
- MPVPE
- 96.3
- Acceleration Error
- 6.6
|
Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation 2023-03-26 |
코드 1 |
| KAMA |
- PA-MPJPE
- 51.1
- MPVPE
- 97.0
|
KAMA: 3D Keypoint Aware Body Mesh Articulation 2021-04-27 |
연결 없음 |
| TRACE |
- PA-MPJPE
- 37.8
- MPJPE
- 79.1
- MPVPE
- 97.3
|
TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments 2023-06-05 |
코드 1 · 코드 2 · 코드 3 |
| TAPE (T=16) |
- PA-MPJPE
- 51.5
- MPJPE
- 79.9
- MPVPE
- 98.1
- Acceleration Error
- 8.9
|
TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation 2023-04-29 |
코드 1 |
| VIBE |
- PA-MPJPE
- 51.9
- MPJPE
- 82.9
- MPVPE
- 99.1
- Acceleration Error
- 23.4
- Number of parameters (M)
- 72.43
|
VIBE: Video Inference for Human Body Pose and Shape Estimation 2019-12-11 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| MPS-Net (T=16) |
- PA-MPJPE
- 52.1
- MPJPE
- 84.3
- MPVPE
- 99.7
- Acceleration Error
- 7.4
- Number of parameters (M)
- 39.63
- FLOPs (G)
- 4.45
|
Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video 2022-03-16 |
연결 없음 |
| CycleAdapt (w/o 2D GT) |
- PA-MPJPE
- 51.1
- MPJPE
- 84.4
- MPVPE
- 99.9
|
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction 2023-08-12 |
코드 1 |
| TePose (T=6) |
- PA-MPJPE
- 52.3
- MPJPE
- 84.6
- MPVPE
- 100.3
- Acceleration Error
- 11.4
|
Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation 2022-07-25 |
코드 1 |
| Self-Attentive |
- PA-MPJPE
- 50.4
- MPJPE
- 85.8
- MPVPE
- 100.6
- Acceleration Error
- 77.9
|
Self-Attentive 3D Human Pose and Shape Estimation from Videos 2021-03-26 |
연결 없음 |
| STR |
- PA-MPJPE
- 52.4
- MPJPE
- 85.2
- MPVPE
- 101.2
- Acceleration Error
- 6.9
|
Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos 2022-10-07 |
연결 없음 |
| DDT |
- PA-MPJPE
- 53.3
- MPJPE
- 85.9
- MPVPE
- 101.2
- Acceleration Error
- 6.6
|
DiffMesh: A Motion-aware Diffusion Framework for Human Mesh Recovery from Videos 2023-03-23 |
연결 없음 |
| CLIFF |
- PA-MPJPE
- 52.7
- MPJPE
- 87.3
- MPVPE
- 102.1
|
3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models 2024-03-17 |
연결 없음 |
| TCMR (T=16 w/o H3.6M) |
- PA-MPJPE
- 52.7
- MPJPE
- 86.5
- MPVPE
- 102.9
- Acceleration Error
- 7.1
|
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video 2020-11-17 |
코드 1 |
| MoCap-SPIN + PoseBERT |
- PA-MPJPE
- 52.9
- MPJPE
- 89.4
- MPVPE
- 103.8
- Acceleration Error
- 8.3
|
Leveraging MoCap Data for Human Mesh Recovery 2021-10-18 |
코드 1 |
| GTRS |
- PA-MPJPE
- 58.9
- MPJPE
- 88.5
- MPVPE
- 106.2
|
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose 2021-11-24 |
코드 1 |
| MUG |
- PA-MPJPE
- 60.5
- MPJPE
- 87
- MPVPE
- 106.2
|
MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose 2022-05-25 |
연결 없음 |
| 3DCrowdNet |
- PA-MPJPE
- 55.8
- MPJPE
- 85.8
- MPVPE
- 108.5
|
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes 2021-04-15 |
코드 1 |
| PC-HMR |
- PA-MPJPE
- 66.9
- MPJPE
- 87.8
- MPVPE
- 108.6
|
PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos 2021-03-16 |
연결 없음 |
| CHOMP |
- PA-MPJPE
- 51.7
- MPJPE
- 83.7
- MPVPE
- 110.1
|
Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior 2022-07-12 |
코드 1 |