Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

3D Multi-Person Pose Estimation (root-relative)

3260 papers • 126 benchmarks • 313 datasets

This task aims to solve root-relative 3D multi-person pose estimation (person-centric coordinate system). No ground truth human bounding box and human root joint coordinates are used during testing stage. ( Image credit: RootNet )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-multi-person-pose-estimation-root-relative-1

Trend

Dataset

Best Model

Actions

MuPoTS-3D

MuPoTS-3D

Libraries

i

Use these libraries to find 3d-multi-person-pose-estimation-root-relative-1 models and implementations

Datasets

MuPoTS-3D

Subtasks

No subtasks available.

Most implemented papers

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

Qi-Xing Huang, Xiao Sun, Yichen Wei, X. Xue, Xingyi Zhou•Fri Apr 07 2017

A weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels.

597

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Single-Shot Multi-person 3D Pose Estimation from Monocular RGB

C. Theobalt, Gerard Pons-Moll, Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar•Fri Dec 08 2017

This work proposes a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera which uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.

434 0

Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB Image

Kyoung Mu Lee, Gyeongsik Moon, Ju Yong Chang•Thu Jul 25 2019

This work firstly proposes a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image, which achieves comparable results with the state-of-the-art 3D single- person pose estimation models without any groundtruth information and significantly outperforms previous 3DMulti-Person pose estimation methods on publicly available datasets.

361 0

Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision

M. Véges, A. Lorincz•Tue Apr 07 2020

This work introduces a network that can be trained with additional RGB-D images in a weakly supervised fashion, and achieves state-of-the-art results on the MuPoTS-3D dataset by a considerable margin.

17 0

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Gim Hee Lee, Jiahao Lin•Thu Jul 16 2020

The Human Depth Estimation Network (HDNet), an end-to-end framework for absolute root joint localization in the camera coordinate space, is proposed and shown to outperform the previous state-of-the-art consistently under multiple evaluation metrics.

34 0

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

Wentao Liu, H. Bao, Xiaowei Zhou, Jiaming Sun, Qi Fang, Wei Jiang, Jianan Zhen•Tue Aug 25 2020

A novel system that first regresses a set of 2.5D representations of body parts and then reconstructs the 3D absolute poses based on these 2.

103 0

Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People

M. Véges, András Lörincz•Fri Oct 30 2020

This work presents an energy minimization approach to generate smooth, valid trajectories in time, bridging gaps in visibility in multi-person pose estimation, and shows that it is better than other interpolation based approaches and achieves state of the art results.

18 0

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

R. Tan, Bo Yang, Yu-Feng Cheng, Bo Wang•Mon Dec 21 2020

This work proposes a novel framework integrating graph convolutional networks (GCNs), which unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results.

50 0

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

R. Tan, Bo Yang, Yu-Feng Cheng, Bo Wang•Sun Apr 04 2021

This work proposes a two-person pose discriminator that enforces natural two- person interactions and applies a semi-supervised method to overcome the 3D ground-truth data scarcity.

40 0

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

Zitian Wang, Yunpeng Chen, Xuecheng Nie, Xiaochao Qu, Siwen Liu•Mon Mar 14 2022

The proposed Distribution-Aware Single-stage DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner, leading to a simplified pipeline with enhanced efficiency and its stat-of-the-art accuracy for multi-person 3D pose estimation.

37 0

Adding a benchmark result helps the community track progress.

3D Multi-Person Pose Estimation (root-relative) | State-of-the-Art