Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

H3WB

Human 3.6M 3D WholeBody

ImagesMIT LicenseIntroduced 2022-11-28

Human3.6M 3D WholeBody (H3WB) is a large scale dataset with 133 whole-body keypoint annotations on 100K images, made possible by a new multi-view pipeline. It is designed for the three new tasks : i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, iii) 3D whole-body pose estimation from a single RGB image.

Source: H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

Image Source: https://arxiv.org/pdf/2211.15692v1.pdf

Benchmarks

1 Image, 2*2 Stitchi/MPJPE 1 Image, 2*2 Stitchi/Average MPJPE (mm)3D/MPJPE 3D/Average MPJPE (mm)3D Face Modelling/Average MPJPE (mm)3D Face Reconstruction/Average MPJPE (mm)3D Hand Pose Estimation/Average MPJPE (mm)3D Human Pose Estimation/MPJPE Face Reconstruction/Average MPJPE (mm)Facial Landmark Detection/Average MPJPE (mm)Facial Recognition and Modelling/Average MPJPE (mm)Hand/Average MPJPE (mm)Hand Pose Estimation/Average MPJPE (mm)Pose Estimation/MPJPE Pose Estimation/Average MPJPE (mm)

Statistics

Papers: 8
Benchmarks: 15

Links

Tasks

1 Image, 2*2 Stitchi 3D 3D Face Modelling 3D Face Reconstruction 3D Facial Landmark Localization 3D Hand Pose Estimation 3D Human Pose Estimation Face Reconstruction Facial Landmark Detection Facial Recognition and Modelling Hand Hand Pose Estimation Monocular 3D Human Pose Estimation Pose Estimation