Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement

07/21/2020
by   Jian Wang, et al.
0

Recently, most of the state-of-the-art human pose estimation methods are based on heatmap regression. The final coordinates of keypoints are obtained by decoding heatmap directly. In this paper, we aim to find a better approach to get more accurate localization results. We mainly put forward two suggestions for improvement: 1) different features and methods should be applied for rough and accurate localization, 2) relationship between keypoints should be considered. Specifically, we propose a two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network. In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled. In the second stage, for each guided point, different visual feature is extracted by the localization subnet. The relationship between guided points is explored by the graph pose refinement module to get more accurate localization results. Experiments show that Graph-PCNN can be used in various backbones to boost the performance by a large margin. Without bells and whistles, our best model can achieve a new state-of-the-art 76.8 test-dev split.

READ FULL TEXT

page 2

page 5

page 6

research
12/10/2018

PoseFix: Model-agnostic General Human Pose Refinement Network

Multi-person pose estimation from a 2D image is an essential technique f...
research
05/07/2021

Probabilistic Visual Place Recognition for Hierarchical Localization

Visual localization techniques often comprise a hierarchical localizatio...
research
03/29/2021

An Adversarial Human Pose Estimation Network Injected with Graph Structure

Because of the invisible human keypoints in images caused by illuminatio...
research
05/15/2021

Composite Localization for Human Pose Estimation

The existing human pose estimation methods are confronted with inaccurat...
research
11/18/2019

The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

Recently, the leading performance of human pose estimation is dominated ...
research
07/18/2023

ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting

Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistenc...
research
01/21/2015

Mirror, mirror on the wall, tell me, is the error small?

Do object part localization methods produce bilaterally symmetric result...

Please sign up or login with your details

Forgot password? Click here to reset