TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/AH36M

AH36M

Ambiguous Human3.6M

ImagesMITIntroduced 2020-11-02

Since H36M is captured in a controlled environment, it rarely depicts challenging real-world scenarios such as body occlusions that are the main source of ambiguity in the single-view 3D shape estimation problem. Hence, we construct an adapted version of H36M with synthetically-generated occlusions by randomly hiding a subset of the 2D keypoints and re-computing an image crop around the remaining visible joints.

Benchmarks

1 Image, 2*2 Stitchi/Best-Hypothesis PMPJPE (n = 25)1 Image, 2*2 Stitchi/H36M PMPJPE (n = 25)1 Image, 2*2 Stitchi/Best-Hypothesis MPJPE (n = 25)1 Image, 2*2 Stitchi/Most-Likely Hypothesis PMPJPE (n = 1)1 Image, 2*2 Stitchi/H36M PMPJPE (n = 1)3D/Best-Hypothesis PMPJPE (n = 25)3D/H36M PMPJPE (n = 25)3D/Best-Hypothesis MPJPE (n = 25)3D/Most-Likely Hypothesis PMPJPE (n = 1)3D/H36M PMPJPE (n = 1)3D Human Pose Estimation/Best-Hypothesis PMPJPE (n = 25)3D Human Pose Estimation/H36M PMPJPE (n = 25)3D Human Pose Estimation/Best-Hypothesis MPJPE (n = 25)3D Human Pose Estimation/Most-Likely Hypothesis PMPJPE (n = 1)3D Human Pose Estimation/H36M PMPJPE (n = 1)Pose Estimation/Best-Hypothesis PMPJPE (n = 25)Pose Estimation/H36M PMPJPE (n = 25)Pose Estimation/Best-Hypothesis MPJPE (n = 25)Pose Estimation/Most-Likely Hypothesis PMPJPE (n = 1)Pose Estimation/H36M PMPJPE (n = 1)

Statistics

Papers
6
Benchmarks
20

Links

Homepage

Tasks

1 Image, 2*2 Stitchi3D3D Human Pose EstimationMulti-Hypotheses 3D Human Pose EstimationPose Estimation