Frequent interactions between individuals are a fundamental challenge for pose estimation algorithms. Current pipelines either use an object detector together with a pose estimator (top-down approach), or localize all body parts first and then link them to predict the pose of individuals (bottom-up). Yet, when individuals closely interact, top-down methods are ill-defined due to overlapping individuals, and bottom-up methods often falsely infer connections to distant body parts. Thus, we propose a novel pipeline called bottom-up conditioned top-down pose estimation (BUCTD) that combines the strengths of bottom-up and top-down methods. Specifically, we propose to use a bottom-up model as the detector, which in addition to an estimated bounding box provides a pose proposal that is fed as condition to an attention-based top-down model. We demonstrate the performance and efficiency of our approach on animal and human pose estimation benchmarks. On CrowdPose and OCHuman, we outperform previous state-of-the-art models by a significant margin. We achieve 78.5 AP on CrowdPose and 47.2 AP on OCHuman, an improvement of 8.6% and 4.9% over the prior art, respectively. Furthermore, we show that our method has excellent performance on non-crowded datasets such as COCO, and strongly improves the performance on multi-animal benchmarks involving mice, fish and monkeys.

翻译：个体间的频繁交互是姿态估计算法面临的一项根本性挑战。当前的主流流程要么采用目标检测器配合姿态估计器（自顶向下方法），要么先定位所有身体部位再将其连接以预测个体姿态（自底向上方法）。然而，当个体紧密交互时，自顶向下方法因个体重叠而定义不清，自底向上方法则常错误地将远距离身体部位建立连接。为此，我们提出一种名为"自底向上条件化自顶向下姿态估计"（BUCTD）的新型流程，融合了自底向上与自顶向下方法的优势。具体而言，我们提议将自底向上模型用作检测器，该模型除提供估计的边界框外，还将生成姿态提议作为条件输入至基于注意力的自顶向下模型。我们在动物与人体姿态估计基准上验证了该方法的性能与效率。在CrowdPose与OCHuman数据集上，我们以显著优势超越了先前的最优模型：在CrowdPose上达到78.5 AP，在OCHuman上达到47.2 AP，分别较先前技术提升8.6%与4.9%。此外，我们证明该方法在COCO等非拥挤数据集上同样表现优异，并显著提升了涉及小鼠、鱼类及猴子的多动物基准上的性能。