DirectPose: Direct End-to-End Multi-Person Pose Estimation

TL;DR

DirectPose introduces a novel end-to-end framework for multi-person pose estimation that directly predicts keypoints without heuristic grouping or bounding-box detection, significantly simplifying the process.

Contribution

It is the first to propose a fully end-to-end multi-person pose estimation framework with a novel Keypoint Alignment mechanism, eliminating the need for traditional heuristic postprocessing.

Findings

Achieves competitive or superior performance compared to existing methods.

Simplifies multi-person pose estimation by removing heuristic grouping.

Maintains end-to-end trainability with a single postprocessing step.

Abstract

We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two corners of target bounding-boxes, the proposed framework directly predicts instance-aware keypoints for all the instances from a raw input image, eliminating the need for heuristic grouping in bottom-up methods or bounding-box detection and RoI operations in top-down ones. We also propose a novel Keypoint Alignment (KPAlign) mechanism, which overcomes the main difficulty: lack of the alignment between the convolutional features and predictions in this end-to-end framework. KPAlign improves the framework's performance by a large margin while still keeping the framework end-to-end trainable. With the only postprocessing non-maximum suppression (NMS), our proposed framework can detect multi-person keypoints with or without bounding-boxes in a single shot. Experiments demonstrate that the end-to-end paradigm can achieve competitive or better performance than previous strong baselines, in both bottom-up and top-down methods. We hope that our end-to-end approach can provide a new perspective for the human pose estimation task.