Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects

Yuki Kawana, YUSUKE Mukuta, Tatsuya Harada

Keywords: unsupervised part decomposition, shape abstraction, 3D shape representations, generative models, computer vision

Abstract: Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent part parsing. In this paper, we propose PPD (unsupervised Pose-aware Part Decomposition) to address a novel setting that explicitly targets man-made articulated objects with mechanical joints, considering the part poses. We show that category-common prior learning for both part shapes and poses facilitates the unsupervised learning of (1) part decomposition with non-primitive-based implicit representation, and (2) part pose as joint parameters under single-frame shape supervision. We evaluate our method on synthetic and real datasets, and we show that it outperforms previous works in consistent part parsing of the articulated objects based on comparable part pose estimation performance to the supervised baseline.

One-sentence Summary: This paper proposes a novel 3D generative model for unsupervised part decomposition that learns to decompose artificial articulated object shapes into part shapes and part poses represented as implicit fields and joint parameters.