Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

In this paper, we study the problem of end-to-end multiperson pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose [38], hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR [27]. We present a simple yet effective transformer approach, named Group Pose. We simply regard K-keypoint pose estimation as predicting a set of N x K keypoint positions, each from a keypoint query, as well as representing each pose with an instance query for scoring N pose predictions. Motivated by the intuition that the interaction, among across-instance queries of different types, is not directly helpful, we make a simple modification to decoder selfattention. We replace single self-attention over all the N x (K + 1) queries with two subsequent group selfattentions: (i) N within-instance self-attention, with each over K keypoint queries and one instance query, and (ii) (K +1) same-type across-instance self-attention, each over N queries of the same type. The resulting decoder removes the interaction among across-instance type-different queries, easing the optimization and thus improving the performance. Experimental results on MS COCO and CrowdPose show that our approach without human box supervision is superior to previous methods with complex decoders, and even is slightly better than ED-Pose that uses human box supervision. Paddle 1 and PyTorch 2 codes are available.