OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

TL;DR

OpenPifPaf introduces a real-time, single-stage neural network framework that detects and tracks semantic keypoints across space and time, suitable for diverse perception tasks including human pose, vehicle, and animal keypoints.

Contribution

The paper presents a novel neural network architecture using Composite Fields for joint spatio-temporal keypoint detection and association, enabling real-time performance.

Findings

Achieves competitive accuracy on COCO, CrowdPose, and PoseTrack datasets.

Operates at an order of magnitude faster than previous methods.

Generalizes to various semantic keypoints beyond humans.

Abstract

Many image-based perception tasks can be formulated as detecting, associating and tracking semantic keypoints, e.g., human body pose estimation and tracking. In this work, we present a general framework that jointly detects and forms spatio-temporal keypoint associations in a single stage, making this the first real-time pose detection and tracking algorithm. We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e.g., a person's body joints) in multiple frames. For the temporal associations, we introduce the Temporal Composite Association Field (TCAF) which requires an extended network architecture and training method beyond previous Composite Fields. Our experiments show competitive accuracy while being an order of magnitude faster on multiple publicly available datasets such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving cars and delivery robots.