We address the task of simultaneous part-level reconstruction and motion
parameter estimation for articulated objects. Given two sets of multi-view
images of an object in two static articulation states, we decouple the movable
part from the static part and reconstruct shape and appearance while predicting
the motion parameters. To tackle this problem, we present PARIS: a
self-supervised, end-to-end architecture that learns part-level implicit shape
and appearance models and optimizes motion parameters jointly without any 3D
supervision, motion, or semantic annotation. Our experiments show that our
method generalizes better across object categories, and outperforms baselines
and prior work that are given 3D point clouds as input. Our approach improves
reconstruction relative to state-of-the-art baselines with a Chamfer-L1
distance reduction of 3.94 (45.2%) for objects and 26.79 (84.5%) for parts, and
achieves 5% error rate for motion estimation across 10 object categories.
Video summary at: this https URL

给定两个静态关节状态下物体的多视图图像，我们提出了一种自我监督的、端到端的架构 PARIS，通过学习部分级隐式形状和外观模型，联合优化运动参数而无需任何 3D 监督、运动或语义标注，以解决关节物体的同时部分重建和运动参数估计的问题。