Multi-person pose estimation using human and keypoint detection with two box processes with ED-Pose
Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2302.01593
arXiv PDF paper https://arxiv.org/pdf/2302.01593.pdf
... presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.
Different from previous one-stage methods, ED-Pose re-considers this task as two explicit box detection processes with a unified representation and regression supervision.
First, ... introduce a human detection decoder from encoded tokens to extract global features ... provide a good initialization for the latter keypoint detection
... Second, to bring in contextual information near keypoints ... regard pose estimation as a keypoint box detection problem to learn both box positions and contents for each keypoint.
A human-to-keypoint detection decoder adopts an interactive learning strategy between human and keypoint features to further enhance global and local feature aggregation.
... ED-Pose surpasses heatmap-based Top-down methods under the same backbone by 1.2 AP on COCO and achieves the state-of-the-art ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments