3D Human Pose Estimation with 2D Marginal Heatmaps

06/05/2018
by   Aiden Nibali, et al.
0

Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult. Recently, researchers have demonstrated that the flexible statistical modelling capabilities of deep neural networks are sufficient to make such inferences with reasonable accuracy. However, many of these models use coordinate output techniques which are memory-intensive, not differentiable, and/or do not spatially generalise well. We propose improvements to 3D coordinate prediction which avoid the aforementioned undesirable traits by predicting 2D marginal heatmaps under an augmented soft-argmax scheme. Our resulting model, MargiPose, produces visually coherent heatmaps whilst maintaining differentiability. We are also able to achieve state-of-the-art accuracy on publicly available 3D human pose estimation data.

READ FULL TEXT
research
03/03/2021

On the role of depth predictions for 3D human pose estimation

Following the successful application of deep convolutional neural networ...
research
12/25/2022

Learning to Estimate 3D Human Pose from Point Cloud

3D pose estimation is a challenging problem in computer vision. Most of ...
research
12/20/2016

3D Human Pose Estimation = 2D Pose Estimation + Matching

We explore 3D human pose estimation from a single RGB image. While many ...
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
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
08/31/2016

Human Pose Estimation in Space and Time using 3D CNN

This paper explores the capabilities of convolutional neural networks to...
research
04/01/2021

Confidence Adaptive Anytime Pixel-Level Recognition

Anytime inference requires a model to make a progression of predictions ...

Please sign up or login with your details

Forgot password? Click here to reset