AI Paper Atlas

Research map / Benchmarks / Human3.6M Protocol 2

Human3.6M Protocol 2 leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Human3.6M Protocol 2. Best MPJPE (mm): 32.1 (HEMlets (Ours), TPAMI 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Human3.6M Protocol 2 · MPJPE (mm)

11 papers, each with its best reported number for its own method; lower is better.

#MPJPE (mm) ↓MethodPaperTopic
132.1HEMlets (Ours)HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation
TPAMI 2021 · Table 1
Human pose estimation
237.7Ours (Full-4s)3D Human Pose Estimation in the Wild by Adversarial Learning
CVPR 2018 · Table 1
Human pose estimation
339Ours (T = 7)Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks
ICCV 2019 · Table 1
Human pose estimation
441.6Ours + Regression #3
Regression #3
Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
CVPR 2019 · Table: Human3.6M results
Human pose estimation
542.3Ours
U-Net (p)
SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera
TPAMI 2020 · Table 9
Human pose estimation
642.6OursGenerating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network
CVPR 2019 · Table: Quantitative results of
Human pose estimation
745.24OursxR-EgoPose: Egocentric 3D Human Pose From an HMD Camera
ICCV 2019 · Table 4
Human pose estimation
847.3Ours, L (20 cells)Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach
ECCV 2020 · Table 6
Human pose estimation
948.6HMOR (Ours)HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
ECCV 2020 · Table 3
Human pose estimation
1053.3Ours (PoseNet, with GT root)Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image
ICCV 2019 · Table 4
Human pose estimation
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.