paper-with-me

3D Human Pose Estimation 벤치마크

3D Human Pose Estimation on EMDB

52개 결과 · ⬇ CSV · JSON

Average MPJPE-PA (mm)

45.7 54.99 64.28 73.56 82.85 2020-08 2026-09 LGD — 81.1389 (2020-08-19) LGD — 81.1389 (2020-08-19) LGD — 81.1389 (2020-08-19) LGD — 81.1389 (2020-08-19) ROMP — 75.1869 (2020-08-27) ROMP — 75.1869 (2020-08-27) ROMP — 75.1869 (2020-08-27) ROMP — 75.1869 (2020-08-27) HybrIK — 65.5935 (2020-11-30) HybrIK — 65.5935 (2020-11-30) HybrIK — 65.5935 (2020-11-30) HybrIK — 65.5935 (2020-11-30) PyMAF — 82.8502 (2021-03-30) PyMAF — 82.8502 (2021-03-30) PyMAF — 82.8502 (2021-03-30) PyMAF — 82.8502 (2021-03-30) PARE — 72.203 (2021-04-17) PARE — 72.203 (2021-04-17) PARE — 72.203 (2021-04-17) PARE — 72.203 (2021-04-17) GLAMR — 71.0091 (2021-12-02) GLAMR — 71.0091 (2021-12-02) GLAMR — 71.0091 (2021-12-02) GLAMR — 71.0091 (2021-12-02) FastMETRO-L no SMPL Head — 66.794 (2022-07-27) FastMETRO-L — 72.6765 (2022-07-27) FastMETRO-L no SMPL Head — 66.794 (2022-07-27) FastMETRO-L — 72.6765 (2022-07-27) FastMETRO-L no SMPL Head — 66.794 (2022-07-27) FastMETRO-L — 72.6765 (2022-07-27) FastMETRO-L no SMPL Head — 66.794 (2022-07-27) FastMETRO-L — 72.6765 (2022-07-27) CLIFF — 68.7969 (2022-08-01) CLIFF — 68.7969 (2022-08-01) CLIFF — 68.7969 (2022-08-01) CLIFF — 68.7969 (2022-08-01) WHAM (ViT) — 50.4 (2023-12-12) WHAM (ViT) — 50.4 (2023-12-12) WHAM (ViT) — 50.4 (2023-12-12) WHAM (ViT) — 50.4 (2023-12-12) TRAM — 45.7 (2024-03-26) TRAM — 45.7 (2024-03-26) TRAM — 45.7 (2024-03-26) TRAM — 45.7 (2024-03-26) GenHMR — 51.7 (2024-12-19) GenHMR — 51.7 (2024-12-19) GenHMR — 51.7 (2024-12-19) GenHMR — 51.7 (2024-12-19) BioPose — 52.1 (2025-01-14) BioPose — 52.1 (2025-01-14) BioPose — 52.1 (2025-01-14) BioPose — 52.1 (2025-01-14) LGD — 81.1389 (2020-08-19) PyMAF — 82.8502 (2021-03-30)
RankModel Average MPJPE-PA (mm)Average MPJPE (mm)Average MVE (mm)Average MVE-PA (mm)Average MPJAE (deg)Average MPJAE-PA (deg)Jitter (10m/s^3) PaperCodeYear
1 TRAM 45.774.486.6–––– TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos yufu-wang/tram 2024
2 WHAM (ViT) 50.479.794.4–––– WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion yohanshin/WHAM 2023
3 GenHMR 51.788.299.5–––– GenHMR: Generative Human Mesh Recovery 2024
4 BioPose 52.192.598.9–––– BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos 2025
5 HybrIK 65.5935103.037122.19380.367824.517423.070449.2068 HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation jeffffffli/HybrIK · Jeff-sjtu/HybrIK · jeff-sjtu/niki · +1 2020
6 FastMETRO-L no SMPL Head 66.794108.107119.2381.1847––185.933 Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers postech-ami/fastmetro 2022
7 CLIFF 68.7969103.134122.88481.327523.093321.626555.4525 CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation huawei-noah/noah-research · xiuyu0000/new_papers_codes · 0jason000/CLIFF · +3 2022
8 GLAMR 71.0091107.797128.23785.458625.505823.548467.3522 GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras nvlabs/glamr 2021
9 PARE 72.203113.887133.24785.378824.67322.384275.1137 PARE: Part Attention Regressor for 3D Human Body Estimation mkocabas/PARE 2021
10 FastMETRO-L 72.6765115.036133.56686.004325.0722.948281.2959 Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers postech-ami/fastmetro 2022
11 ROMP 75.1869112.652134.86390.64826.597523.990171.2556 Monocular, One-stage, Regression of Multiple 3D People Arthur151/ROMP · cai-jianfeng/ROMP_mindspore 2020
12 LGD 81.1389115.82140.6395.725525.157225.642572.9695 Human Body Model Fitting by Learned Gradient Descent 2020
13 PyMAF 82.8502131.065159.95698.130528.455525.703381.8447 PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop HongwenZhang/PyMAF · Droliven/pymaf_reimplementation 2021
14 TRAM 45.774.486.6–––– TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos yufu-wang/tram 2024
15 WHAM (ViT) 50.479.794.4–––– WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion yohanshin/WHAM 2023
16 GenHMR 51.788.299.5–––– GenHMR: Generative Human Mesh Recovery 2024
17 BioPose 52.192.598.9–––– BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos 2025
18 HybrIK 65.5935103.037122.19380.367824.517423.070449.2068 HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation jeffffffli/HybrIK · Jeff-sjtu/HybrIK · jeff-sjtu/niki · +1 2020
19 FastMETRO-L no SMPL Head 66.794108.107119.2381.1847––185.933 Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers postech-ami/fastmetro 2022
20 CLIFF 68.7969103.134122.88481.327523.093321.626555.4525 CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation huawei-noah/noah-research · xiuyu0000/new_papers_codes · 0jason000/CLIFF · +3 2022
1–20 / 52 다음 → 페이지당 10 20 50 100