Browse › Computer Vision › Monocular 3D Human Pose Estimation › Human3.6M

Monocular 3D Human Pose Estimation archive 2025-07-28

Human3.6M Benchmark (Monocular 3D Human Pose Estimation)

52 rows 45 with code listed 6 metrics Dataset page

This task targets at 3D human pose estimation with a single RGB camera.

The archive carries no text for this table; the description above is the archive's text for the task Monocular 3D Human Pose Estimation. archive 2025-07-28

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Not inferred: Average MPJPE (mm), Use Video Sequence, Frames Needed, Need Ground Truth 2D Pose, PA-MPJPE, 2D detector. Points are placed at the row's paper date; 52 of 52 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 MotionBERT (Finetune) 37.5Yes243NoSH ✓ Paper Code 2022 5 of 11 ran · 6 unverified report
2 MotionAGFormer-L 38.4Yes243NoSH – Paper Code 2023 14 of 16 ran · 2 unverified report
3 MotionAGFormer-B 38.4Yes243NoSH – Paper Code 2023 14 of 16 ran · 2 unverified report
4 MotionBERT (Scratch) 39.2Yes243NoSH – Paper Code 2022 5 of 11 ran · 6 unverified report
5 D3DP 39.5Yes243NoCPN – Paper Code 2023 0 of 2 ran · 2 unverified report
6 DDHPose 39.7Yes243NoCPN – Paper Code 2024 linked, not harvested report
7 MixSTE (HRNet, T=243) 39.8Yes243NoHRNet – Paper Code 2022 4 of 4 ran · 0 unverified report
8 HEMlets Pose (H36M+MPII) 39.9127.9 – Paper – 2019 no code linked report
9 Spatio-Temporal Network (T=128) 40.1Yes128No30.7 – Paper – 2020 no code linked report
10 KTPFormer 40.1Yes243NoCPN – Paper Code 2024 6 of 10 ran · 4 unverified report
11 GenHMR 41.229.8 – Paper – 2024 no code linked report
12 P-STMO (N=243) 42.1Yes243NoCPN – Paper Code 2022 9 of 11 ran · 2 unverified report
13 MotionAGFormer-S 42.5Yes81NoSH – Paper Code 2023 14 of 16 ran · 2 unverified report
14 Anatomy3D 44.1Yes243NoCPN – Paper Code 2020 linked, not harvested report
15 PoseFormer (T=81) 44.381CPN – Paper Code 2021 4 of 8 ran · 4 unverified report
16 RIE (T=243 CPN) 44.3Yes243NoCPN – Paper Code 2021 linked, not harvested report
17 MotionAGFormer-XS 45.1Yes27NoSH – Paper Code 2023 14 of 16 ran · 2 unverified report
18 Attention3DHumanPose 45.1Yes243NoCPN – Paper Code 2020 linked, not harvested report
19 Trajectory Space Factorization (50 frames) 46.6Yes50No – Paper Code 2019 linked, not harvested report
20 VideoPose3D (T=243) 46.8Yes243NoCPN – Paper Code 2018 0 of 2 ran · 2 unverified report
21 PointHMR 48.332.9 ✓ Paper Code 2023 5 of 8 ran · 3 unverified report
22 SRNET 49.9No1No – Paper Code 2020 1 of 9 ran · 8 unverified report
23 HR-Net+VPose+PoseAug 50.239.1 – Paper Code 2021 linked, not harvested report
24 TAG-Net 50.9No1No – Paper Code 2020 2 of 2 ran · 0 unverified report
25 cross-dataset-evaluation 52.0No1No ✓ Paper – 2020 no code linked report
26 TP-Net 52.1Yes20No – Paper Code 2017 linked, not harvested report
27 Multimodal Mixture Density Networks 52.7No1No – Paper Code 2019 1 of 11 ran · 10 unverified report
28 SemGCN 57.6No1No – Paper Code 2019 2 of 8 ran · 6 unverified report
29 MultiPoseNet 58.0No1No – Paper Code 2019 0 of 3 ran · 3 unverified report
30 Monocular Total Capture 58.3NO1No – Paper Code 2018 linked, not harvested report
31 SIM (SH detections FT) (MA) 62.9No1No – Paper Code 2017 5 of 7 ran · 2 unverified report
32 Bundle Adjustment (GTi) 63.3 – Paper Code 2019 0 of 3 ran · 3 unverified report
33 SelecSLS 63.6No1No – Paper Code 2019 linked, not harvested report
34 Weakly Supervised Transfer Learning 64.9No1No – Paper Code 2017 linked, not harvested report
35 VIBE 65.6Yes16No – Paper Code 2019 0 of 1 ran · 1 unverified report
36 GraphCMR 74.7No1No – Paper Code 2019 2 of 7 ran · 5 unverified report
37 Projected-pose belief maps + 2D fusion layers 88.39No1No – Paper Code 2017 linked, not harvested report
38 RepNet 89.9No1No – Paper Code 2019 linked, not harvested report
39 Dual-source approach 97.39No1No – Paper – 2017 no code linked report
40 Sparseness Meets Deepness 113.01Yes300No – Paper Code 2015 linked, not harvested report
41 HMR No1No – Paper Code 2017 linked, not harvested report
42 Neural Body Fitting (NBF) No1No – Paper Code 2018 1 of 1 ran · 0 unverified report
43 SMPLify (dense) No1No – Paper Code 2017 1 of 1 ran · 0 unverified report
44 Ordinal Depth Supervision No1No – Paper Code 2018 linked, not harvested report
45 Adversarial Learning No1No – Paper – 2018 no code linked report
46 Moon et. al. No1No – Paper Code 2019 1 of 7 ran · 6 unverified report
47 PoseAug No1No – Paper Code 2021 linked, not harvested report
48 HEMlets Pose No1No ✓ Paper – 2019 no code linked report
49 Ray3D Yes9No – Paper Code 2022 4 of 5 ran · 1 unverified report
50 Bundle Adjustment Yes190No – Paper Code 2019 0 of 3 ran · 3 unverified report
51 Neural Body Fitting (NBF) 59.9 – Paper Code 2018 1 of 1 ran · 0 unverified report
52 SMPLify (dense) 80.7 – Paper Code 2017 1 of 1 ran · 0 unverified report

All 52 rows shown. 52 link to a paper page on this site; 4 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 29 rows have a graph line, from 22 distinct papers; 23 rows (17 papers) have at least one sample that ran. Counting each paper once: Syntology ran 67 of 137 samples; 70 unverified. Separately, 28 of those 137 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections