Multi-Person Full Body Pose Estimation

TL;DR

This paper introduces an integrated multi-person full body pose estimation model using knowledge distillation, achieving 51.5 mAP on the MSCOCO2017 dataset, advancing the accuracy of multi-person pose estimation.

Contribution

The work presents a novel integrated model for full body pose estimation in multi-person scenarios, utilizing knowledge distillation to improve performance.

Findings

Achieved 51.5 mAP on MSCOCO2017 validation dataset.

Developed an integrated model trained on AlphaPose and MSCOCO2017.

Provides resources and code at the specified URL.

Abstract

Multi-person pose estimation plays an important role in many fields. Although previous works have researched a lot on different parts of human pose estimation, full body pose estimation for multi-person still needs further research. Our work has developed an integrated model through knowledge distillation which can estimate full body poses. Trained based on the AlphaPose system and MSCOCO2017 dataset, our model achieves 51.5 mAP on the validation dataset annotated manually by ourselves. Related resources are available at https://esflfei.github.io/esflfei.gethub.io/website.html.