End-to-End Trainable Multi-Instance Pose Estimation with Transformers

03/22/2021
by   Lucas Stoffl, et al.
0

We propose a new end-to-end trainable approach for multi-instance pose estimation by combining a convolutional neural network with a transformer. We cast multi-instance pose estimation from images as a direct set prediction problem. Inspired by recent work on end-to-end trainable object detection with transformers, we use a transformer encoder-decoder architecture together with a bipartite matching scheme to directly regress the pose of all individuals in a given image. Our model, called POse Estimation Transformer (POET), is trained using a novel set-based global loss that consists of a keypoint loss, a keypoint visibility loss, a center loss and a class loss. POET reasons about the relations between detected humans and the full image context to directly predict the poses in parallel. We show that POET can achieve high accuracy on the challenging COCO keypoint detection task. To the best of our knowledge, this model is the first end-to-end trainable multi-instance human pose estimation method.

READ FULL TEXT

page 1

page 2

page 3

page 6

page 7

research
05/05/2022

YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression

6D object pose estimation is a crucial prerequisite for autonomous robot...
research
07/21/2023

YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation

6D object pose estimation is a crucial prerequisite for autonomous robot...
research
09/08/2021

Learning Local-Global Contextual Adaptation for Fully End-to-End Bottom-Up Human Pose Estimation

This paper presents a method of learning Local-GlObal Contextual Adaptat...
research
04/02/2021

End-to-end learning of keypoint detection and matching for relative pose estimation

We propose a new method for estimating the relative pose between two ima...
research
05/10/2016

Recurrent Human Pose Estimation

We propose a novel ConvNet model for predicting 2D human body poses in a...
research
07/05/2018

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

This paper presents KeypointNet, an end-to-end geometric reasoning frame...
research
02/07/2022

HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders

In this paper, HeadPosr is proposed to predict the head poses using a si...

Please sign up or login with your details

Forgot password? Click here to reset