Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

04/01/2020
by   Matteo Fabbri, et al.
4

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective compression method to drastically reduce the size of this representation. At the core of the proposed method lies our Volumetric Heatmap Autoencoder, a fully-convolutional network tasked with the compression of ground-truth heatmaps into a dense intermediate representation. A second model, the Code Predictor, is then trained to predict these codes, which can be decompressed at test time to re-obtain the original representation. Our experimental evaluation shows that our method performs favorably when compared to state of the art on both multi-person and single-person 3D human pose estimation datasets and, thanks to our novel compression strategy, can process full-HD images at the constant runtime of 8 fps regardless of the number of subjects in the scene. Code and models available at https://github.com/fabbrimatteo/LoCO .

READ FULL TEXT

page 1

page 7

page 8

page 13

research
07/26/2019

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

Although significant improvement has been achieved in 3D human pose esti...
research
04/29/2022

A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Many human pose estimation methods estimate Skinned Multi-Person Linear ...
research
03/05/2020

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

Heatmap representations have formed the basis of 2D human pose estimatio...
research
10/14/2021

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

We introduce HUMAN4D, a large and multimodal 4D dataset that contains a ...
research
03/30/2019

Can WiFi Estimate Person Pose?

WiFi human sensing has achieved great progress in indoor localization, a...
research
10/11/2020

PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation

Recent literature addressed the monocular 3D pose estimation task very s...
research
04/06/2020

Light3DPose: Real-time Multi-Person 3D PoseEstimation from Multiple Views

We present an approach to perform 3D pose estimation of multiple people ...

Please sign up or login with your details

Forgot password? Click here to reset