arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.07313cs.CV
收藏

Group Pose:端到端多人姿态估计的简单基线

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

Beijing Jiaotong University(北京交通大学);Baidu VIS(百度视觉技术部)

Huan Liu, Qiang Chen, Zichang Tan, Jiang-Jiang Liu, Jian Wang, Xiangbo Su, Xiaolong Li, Kun Yao, Junyu Han, Errui Ding, Yao Zhao, Jingdong Wang

AI总结:

针对端到端多人姿态估计,本文提出Group Pose,通过实例内与同类型跨实例的分组自注意力简化类DETR解码器,在无人体框监督下于MS COCO和CrowdPose上取得优于复杂方法的性能。

摘要:

本文研究端到端多人姿态估计问题。当前最先进的解决方案采用类DETR框架,且主要开发复杂的解码器,例如在ED-Pose中将姿态估计视为关键点框检测并与人体检测相结合,在PETR中通过姿态解码器和关节(关键点)解码器进行层级化预测。我们提出一种简单而有效的transformer方法,名为Group Pose。我们直接将K关键点姿态估计视为预测一组N×K个关键点位置,每个位置来自一个关键点查询,同时用一个实例查询表示每个姿态,以便对N个姿态预测进行评分。受不同类型的跨实例查询之间的交互并无直接帮助这一直觉启发,我们对解码器自注意力进行了简单修改。我们将覆盖全部N×(K+1)个查询的单个自注意力替换为两个连续的分组自注意力:(i)N个实例内自注意力,每个在K个关键点查询和一个实例查询上进行;(ii)(K+1)个同类型跨实例自注意力,每个在N个同类型查询上进行。所得解码器消除了跨实例的不同类型查询之间的交互,使优化更容易,从而提升性能。在MS COCO和CrowdPose上的实验结果表明,我们的方法无需人体框监督,即优于此前采用复杂解码器的方法,甚至略优于使用人体框监督的ED-Pose。Paddle和PyTorch代码均已公开。

英文摘要:

In this paper, we study the problem of end-to-end multi-person 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, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR. We present a simple yet effective transformer approach, named Group Pose. We simply regard $K$-keypoint pose estimation as predicting a set of $N\times K$ 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 self-attention. We replace single self-attention over all the $N\times(K+1)$ queries with two subsequent group self-attentions: (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. $\href{https://github.com/Michel-liu/GroupPose-Paddle}{\rm Paddle}$ and $\href{https://github.com/Michel-liu/GroupPose}{\rm PyTorch}$ code are available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑