Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
7/26/2019
cs.CV

Official code: mks0601/3DMPPE_POSENET_RELEASE (865 stars, MIT, PyTorch, last commit 2024-07-10). 1 more implementation below.

Abstract

Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.

View on arXivView PDF

Code Implementations(2)

mks0601/3DMPPE_POSENET_RELEASEOfficial100%
PyTorchMIT

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

865146Jul 22, 20192 years agoMIT
3d-human-posecomputer-visiondeep-learninghuman-pose-estimationiccv2019+1 more
mks0601/3DMPPE_ROOTNET_RELEASEOfficial100%
PyTorchMIT

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

49266PythonJul 22, 20192 years agoMIT
3d-human-posecomputer-visiondeep-learninghuman-pose-estimationiccv2019+1 more

Similar Papers

OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

88% match1 repo34.5k2018

UniPose: Unified Human Pose Estimation in Single Images and Videos

87% match1 repo2232020

Improving Real-Time Omnidirectional 3D Multi-Person Human Pose Estimation with People Matching and Unsupervised 2D-3D Lifting

86% match2024

Towards High Performance One-Stage Human Pose Estimation

86% match2023

Unsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone

86% match2023

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

85% match2 repos8.6k2022

Cite this paper

@article{moon2019camera,
  title  = {Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image},
  author = {Gyeongsik Moon and Ju Yong Chang and Kyoung Mu Lee},
  year   = {2019},
  eprint = {1907.11346},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1907.11346}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1907.11346.svg)](https://codeofpaper.com/paper/1907.11346)

Discussion