TFPose: Direct Human Pose Estimation with Transformers

03/29/2021
by   Weian Mao, et al.
0

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcomes the feature misalignment issue of previous regression-based methods and considerably improves the performance. Importantly, our framework can inherently take advantages of the structured relationship between keypoints. Experiments on the MS-COCO and MPII datasets demonstrate that our method can significantly improve the state-of-the-art of regression-based pose estimation and perform comparably with the best heatmap-based pose estimation methods.

READ FULL TEXT

page 1

page 3

page 7

page 12

page 13

page 14

page 15

research
01/19/2022

Poseur: Direct Human Pose Regression with Transformers

We propose a direct, regression-based approach to 2D human pose estimati...
research
04/12/2023

Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation

Human pose estimation has seen widespread use of transformer models in r...
research
04/01/2017

Compositional Human Pose Regression

Regression based methods are not performing as well as detection based m...
research
12/30/2020

Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation

Heatmap regression has become the most prevalent choice for nowadays hum...
research
09/22/2021

T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression

6D pose estimation is the task of predicting the translation and orienta...
research
02/15/2023

Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation

There has been a recent surge of interest in introducing transformers to...
research
10/13/2020

LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization

We present LM-Reloc – a novel approach for visual relocalization based o...

Please sign up or login with your details

Forgot password? Click here to reset