Single-stage multi-person human pose estimation (MPPE) methods have shown
great performance improvements, but existing methods fail to disentangle
features by individual instances under crowded scenes. In this paper, we
propose a bounding box-level instance representation learning called BoIR,
which simultaneously solves instance detection, instance disentanglement, and
instance-keypoint association problems. Our new instance embedding loss
provides a learning signal on the entire area of the image with bounding box
annotations, achieving globally consistent and disentangled instance
representation. Our method exploits multi-task learning of bottom-up keypoint
estimation, bounding box regression, and contrastive instance embedding
learning, without additional computational cost during inference. BoIR is
effective for crowded scenes, outperforming state-of-the-art on COCO val (0.8
AP), COCO test-dev (0.5 AP), CrowdPose (4.9 AP), and OCHuman (3.5 AP). Code
will be available at this https URL

本文提出了一种称为 BoIR 的边界框级实例表示学习方法，通过解决实例检测、实例解开和实例 - 关键点关联问题，同时解决了拥挤场景下的特征分离问题。我们的方法通过多任务学习底层关键点估计、边界框回归和对比实例嵌入学习，在推理过程中没有额外的计算成本，并在 COCO val（0.8 AP）、COCO test-dev（0.5 AP）、CrowdPose（4.9 AP）和 OCHuman（3.5 AP）等数据集上表现优于现有方法。