3DCrowdNet: 2D Human Pose-Guided3D Crowd Human Pose and Shape Estimation in the Wild

04/15/2021
by   Hongsuk Choi, et al.
0

Recovering accurate 3D human pose and shape from in-the-wild crowd scenes is highly challenging and barely studied, despite their common presence. In this regard, we present 3DCrowdNet, a 2D human pose-guided 3D crowd pose and shape estimation system for in-the-wild scenes. 2D human pose estimation methods provide relatively robust outputs on crowd scenes than 3D human pose estimation methods, as they can exploit in-the-wild multi-person 2D datasets that include crowd scenes. On the other hand, the 3D methods leverage 3D datasets, of which images mostly contain a single actor without a crowd. The train data difference impedes the 3D methods' ability to focus on a target person in in-the-wild crowd scenes. Thus, we design our system to leverage the robust 2D pose outputs from off-the-shelf 2D pose estimators, which guide a network to focus on a target person and provide essential human articulation information. We show that our 3DCrowdNet outperforms previous methods on in-the-wild crowd scenes. We will release the codes.

READ FULL TEXT

page 1

page 2

page 6

page 8

page 9

page 10

page 11

page 12

research
10/27/2017

Dual Path Networks for Multi-Person Human Pose Estimation

The task of multi-person human pose estimation in natural scenes is quit...
research
12/04/2020

SMPLy Benchmarking 3D Human Pose Estimation in the Wild

Predicting 3D human pose from images has seen great recent improvements....
research
05/10/2019

Exploiting temporal context for 3D human pose estimation in the wild

We present a bundle-adjustment-based algorithm for recovering accurate 3...
research
04/05/2019

In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations

Convolutional Neural Network based approaches for monocular 3D human pos...
research
11/23/2020

NeuralAnnot: Neural Annotator for in-the-wild Expressive 3D Human Pose and Mesh Training Sets

Recovering expressive 3D human pose and mesh from in-the-wild images is ...
research
03/07/2020

PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation

Recovering 3D human pose from 2D joints is a highly unconstrained proble...
research
09/10/2023

FreeMan: Towards Benchmarking 3D Human Pose Estimation in the Wild

Estimating the 3D structure of the human body from natural scenes is a f...

Please sign up or login with your details

Forgot password? Click here to reset