The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

MCML Authors

Guillem Brasó

* Former Member

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Laura Leal-Taixé

Prof. Dr.

Principal Investigator

* Former Principal Investigator

Abstract

We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up approaches.

inproceedings BKL21

---

ICCV 2021

IEEE/CVF International Conference on Computer Vision. Virtual, Oct 11-17, 2021.

---

Authors

G. Brasó • N. Kister • L. Leal-Taixé

---

Links

DOI GitHub

---

Research Area

 B1 | Computer Vision