# Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry

Source: [Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry](<https://www.sota2.com/research/paper/68fa68081e209131cea19a58>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:16:30.879Z

Authors: He Chen, Pengfei Guo, Pengfei Li, Gim Hee Lee, Gregory Chirikjian

Published: 2020-07-21T17:59:36.000Z

## Abstract

Epipolar constraints are at the core of feature matching and depth estimation in current multi-person multi-camera 3D human pose estimation methods. Despite the satisfactory performance of this formulation in sparser crowd scenes, its effectiveness is frequently challenged under denser crowd circumstances mainly due to two sources of ambiguity. The first is the mismatch of human joints resulting from the simple cues provided by the Euclidean distances between joints and epipolar lines. The second is the lack of robustness from the naive formulation of the problem as a least squares minimization. In this paper, we depart from the multi-person 3D pose estimation formulation, and instead reformulate it as crowd pose estimation. Our method consists of two key components: a graph model for fast cross-view matching, and a maximum a posteriori (MAP) estimator for the reconstruction of the 3D human poses. We demonstrate the effectiveness and superiority of our proposed method on four benchmark datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Human Pose Estimation on Chariot Mk I](<https://www.sota2.com/research/sota/3d-human-pose-estimation-on-chariot-mk-i.md>): 3D Human Pose Estimation; Chariot Mk I; AP: 89.8.

- [3D Human Pose Estimation on LOEWENPLATZ](<https://www.sota2.com/research/sota/3d-human-pose-estimation-on-loewenplatz.md>): 3D Human Pose Estimation; LOEWENPLATZ; AP: 81.8.

- [3D Human Pose Estimation on Wildtrack](<https://www.sota2.com/research/sota/3d-human-pose-estimation-on-wildtrack.md>): 3D Human Pose Estimation; Wildtrack; AP: 70.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.10986>)

[PDF](<https://arxiv.org/pdf/2007.10986.pdf>)

[Implementation](<https://github.com/HeCraneChen/3D-Crowd-Pose-Estimation-Based-on-MVG>)