A key assumption of top-down human pose estimation approaches is their expectation of having a single person present in the input bounding box. This often leads to failures in crowded scenes with occlusions. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Hypothesis Pose Network (MHPNet) allows for predicting multiple 2D poses within a given bounding box. We introduce a Multi-Hypothesis Attention Block (MHAB) that can adaptively modulate channel-wise feature responses for each hypothesis and is parameter efficient. We demonstrate the efficacy of our approach by evaluating on COCO, CrowdPose, and OCHuman datasets. Specifically, we achieve 70.0 AP on CrowdPose and 42.5 AP on OCHuman test sets, a significant improvement of 2.4 AP and 6.5 AP over the prior art, respectively. When using ground truth bounding boxes for inference, MHPNet achieves an improvement of 0.7 AP on COCO, 0.9 AP on CrowdPose, and 9.1 AP on OCHuman validation sets compared to HRNet. Interestingly, when fewer, high confidence bounding boxes are used, HRNet's performance degrades (by 5 AP) on OCHuman, whereas MHPNet maintains a relatively stable performance (a drop of 1 AP) for the same inputs.

提出了一种名为Multi-Instance Pose Network (MIPNet)的人体姿势估计模型，能够在给定边框范围内预测多个2D姿态实例，并引入了一种称为多实例调制块（Multi-Instance Modulation Block，MIMB）的方法来适应性地调制每个实例的通道特征响应，与以往方法相比，在复杂场景中取得了显著的性能提升。

多实例姿态网络：重新思考自上而下的姿态估计