Accurate human shape recovery from a monocular RGB image is a challenging task because humans come in different shapes and sizes and wear different clothes. In this paper, we propose ShapeBoost, a new human shape recovery framework that achieves pixel-level alignment even for rare body shapes and high accuracy for people wearing different types of clothes. Unlike previous approaches that rely on the use of PCA-based shape coefficients, we adopt a new human shape parameterization that decomposes the human shape into bone lengths and the mean width of each part slice. This part-based parameterization technique achieves a balance between flexibility and validity using a semi-analytical shape reconstruction algorithm. Based on this new parameterization, a clothing-preserving data augmentation module is proposed to generate realistic images with diverse body shapes and accurate annotations. Experimental results show that our method outperforms other state-of-the-art methods in diverse body shape situations as well as in varied clothing situations.

翻译：从单张RGB图像中准确恢复人体形状是一项极具挑战性的任务，因为人类具有不同的体型、尺寸并穿着不同的衣物。本文提出ShapeBoost——一种新型人体形状恢复框架，即使在罕见体型条件下也能实现像素级对齐，并对穿着不同衣物的个体保持高精度。不同于以往依赖基于PCA的形状系数的方法，我们采用了一种新的人体形状参数化方法，将人体形状分解为骨骼长度和每个部位切片的平均宽度。这种基于部位的参数化技术通过半解析形状重建算法在灵活性和有效性之间取得了平衡。基于该参数化方法，我们进一步提出了一种衣物保持的数据增强模块，可生成具有多样化体型的逼真图像及其精确标注。实验结果表明，我们的方法在多种体型及衣物场景下均优于当前最先进方法。