Poseur: Direct Human Pose Regression with Transformers

01/19/2022
by   Weian Mao, et al.
4

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.

READ FULL TEXT

page 4

page 7

research
03/29/2021

TFPose: Direct Human Pose Estimation with Transformers

We propose a human pose estimation framework that solves the task in the...
research
10/06/2017

Human Pose Regression by Combining Indirect Part Detection and Contextual Information

In this paper, we propose an end-to-end trainable regression approach fo...
research
04/14/2021

Pose Recognition with Cascade Transformers

In this paper, we present a regression-based pose recognition method usi...
research
05/02/2023

Hybrid model for Single-Stage Multi-Person Pose Estimation

In general, human pose estimation methods are categorized into two appro...
research
05/08/2021

Improving Robustness for Pose Estimation via Stable Heatmap Regression

Deep learning methods have achieved excellent performance in pose estima...
research
08/06/2022

IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation

Video 3D human pose estimation aims to localize the 3D coordinates of hu...
research
01/25/2023

Bias-Compensated Integral Regression for Human Pose Estimation

In human and hand pose estimation, heatmaps are a crucial intermediate r...

Please sign up or login with your details

Forgot password? Click here to reset