← Monocular 3D Human Pose Estimation
평가 기록
과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.
표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.
| 모델 | 원본 지표·값 | 논문 | 구현 |
|---|---|---|---|
| MotionBERT (Finetune) |
|
MotionBERT: A Unified Perspective on Learning Human Motion Representations 2022-10-12 |
코드 1 |
| MotionAGFormer-L |
|
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network 2023-10-25 |
코드 1 |
| MotionAGFormer-B |
|
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network 2023-10-25 |
코드 1 |
| MotionBERT (Scratch) |
|
MotionBERT: A Unified Perspective on Learning Human Motion Representations 2022-10-12 |
코드 1 |
| D3DP |
|
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation 2023-03-21 |
코드 1 |
| DDHPose |
|
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser 2024-03-07 |
코드 1 |
| MixSTE (HRNet, T=243) |
|
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video 2022-03-02 |
코드 1 |
| HEMlets Pose (H36M+MPII) |
|
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation 2019-10-26 |
연결 없음 |
| Spatio-Temporal Network (T=128) |
|
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training 2020-04-07 |
연결 없음 |
| KTPFormer |
|
KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation 2024-03-31 |
코드 1 |
| GenHMR |
|
GenHMR: Generative Human Mesh Recovery 2024-12-19 |
연결 없음 |
| P-STMO (N=243) |
|
P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation 2022-03-15 |
코드 1 |
| MotionAGFormer-S |
|
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network 2023-10-25 |
코드 1 |
| Anatomy3D |
|
Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition 2020-02-24 |
코드 1 |
| PoseFormer (T=81) |
|
3D Human Pose Estimation with Spatial and Temporal Transformers 2021-03-18 |
코드 1 · 코드 2 · 코드 3 |
| RIE (T=243 CPN) |
|
Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation 2021-07-29 |
코드 1 |
| MotionAGFormer-XS |
|
MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network 2023-10-25 |
코드 1 |
| Attention3DHumanPose |
|
Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction 2020-06-01 |
코드 1 |
| Trajectory Space Factorization (50 frames) |
|
Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation 2019-08-22 |
코드 1 |
| VideoPose3D (T=243) |
|
3D human pose estimation in video with temporal convolutions and semi-supervised training 2018-11-28 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 |
| PointHMR |
|
Sampling is Matter: Point-guided 3D Human Mesh Reconstruction 2023-04-19 |
코드 1 |
| SRNET |
|
SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach 2020-07-18 |
코드 1 |
| HR-Net+VPose+PoseAug |
|
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation 2021-05-06 |
코드 1 |
| TAG-Net |
|
Cascaded deep monocular 3D human pose estimation with evolutionary training data 2020-06-14 |
코드 1 |
| cross-dataset-evaluation |
|
Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation 2020-04-07 |
연결 없음 |
| TP-Net |
|
Learning 3D Human Pose from Structure and Motion 2017-11-25 |
코드 1 |
| Multimodal Mixture Density Networks |
|
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network 2019-04-11 |
코드 1 · 코드 2 |
| SemGCN |
|
Semantic Graph Convolutional Networks for 3D Human Pose Regression 2019-04-06 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| MultiPoseNet |
|
Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking 2019-04-02 |
코드 1 |
| Monocular Total Capture |
|
Monocular Total Capture: Posing Face, Body, and Hands in the Wild 2018-12-04 |
코드 1 |