This paper presents a novel approach for estimating human body shape and pose from monocular images that effectively addresses the challenges of occlusions and depth ambiguity. Our proposed method BoPR, the Body-aware Part Regressor, first extracts features of both the body and part regions using an attention-guided mechanism. We then utilize these features to encode extra part-body dependency for per-part regression, with part features as queries and body feature as a reference. This allows our network to infer the spatial relationship of occluded parts with the body by leveraging visible parts and body reference information. Our method outperforms existing state-of-the-art methods on two benchmark datasets, and our experiments show that it significantly surpasses existing methods in terms of depth ambiguity and occlusion handling. These results provide strong evidence of the effectiveness of our approach.The code and data are available for research purposes at https://github.com/cyk990422/BoPR.
翻译:本文提出了一种新颖的方法,用于从单眼图像中估计人体形状和姿态,并有效地解决了遮挡和深度模糊的挑战。我们提出的方法BoPR(Body-aware Part Regressor)首先使用注意力引导机制提取身体和部位区域的特征。然后,我们利用这些特征对每一部分进行编码,以实现部分与身体的附加依赖性回归,其中部分特征作为查询,身体特征作为参考。这使我们的网络通过利用可见部分和身体参考信息推断遮挡部分与身体的空间关系。我们的方法在两个基准数据集上均优于现有最先进的方法,并且我们的实验表明,它在处理深度模糊和遮挡方面显著优于现有方法。这些结果强有力地证明了我们方法的有效性。代码和数据可在https://github.com/cyk990422/BoPR上供研究目的使用。