ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild

08/23/2022
by   Lumin Xu, et al.
6

This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.

READ FULL TEXT

page 1

page 6

page 8

page 9

page 13

page 18

research
07/23/2020

Whole-Body Human Pose Estimation in the Wild

This paper investigates the task of 2D human whole-body pose estimation,...
research
02/01/2018

DensePose: Dense Human Pose Estimation In The Wild

In this work, we establish dense correspondences between RGB image and a...
research
11/27/2020

MEBOW: Monocular Estimation of Body Orientation In the Wild

Body orientation estimation provides crucial visual cues in many applica...
research
11/28/2022

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

3D human whole-body pose estimation aims to localize precise 3D keypoint...
research
12/13/2020

EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search

Human pose estimation from image and video is a vital task in many multi...
research
08/13/2021

FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration

Most existing monocular 3D pose estimation approaches only focus on a si...
research
11/17/2020

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution

Neural architecture search has proven to be highly effective in the desi...

Please sign up or login with your details

Forgot password? Click here to reset