DirectPose: Direct End-to-End Multi-Person Pose Estimation
This work addresses the challenge of simplifying and improving efficiency in human pose estimation for computer vision applications, though it is incremental as it builds on anchor-free object detection ideas.
The authors tackled the problem of multi-person pose estimation by introducing DirectPose, the first direct end-to-end framework that predicts instance-aware keypoints from raw images, eliminating heuristic grouping or bounding-box detection. The framework, enhanced with a Keypoint Alignment mechanism, achieves competitive or better performance than previous baselines in both bottom-up and top-down methods.
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.