POET: End-to-End Multi-Instance Pose Estimation with Transformers

This repository contains the official implementation of POET (POse Estimation Transformer) and is build built on top of DETR. We replace the full complex hand-crafted pose estimation pipeline with a Transformer, and outperform Associative Embedding with a ResNet-50, obtaining 54 mAP on COCO.

For details see End-to-End Trainable Multi-Instance Pose Estimation with Transformers by Lucas Stoffl, Maxime Vidal and Alexander Mathis.

Notebooks

We provide a few notebooks to help you get a grasp on POET:

• POET's demo notebook: Shows how to load a pre-trained model, generate predictions and visualize the attention of the model.

License

POET is released under the Apache 2.0 license. Please see the LICENSE file for more information.