Articulated objects are pervasive in daily environments, such as drawers and refrigerators. Towards their part-level surface reconstruction and joint parameter estimation, REArtGS introduces a category-agnostic approach using multi-view RGB images at two different states. However, we observe that REArtGS still struggles with screw-joint or multi-part objects and lacks geometric constraints for unseen states. In this paper, we propose REArtGS++, a novel method towards generalizable articulated object reconstruction with temporal geometry constraint and planar Gaussian splatting. We first model a decoupled screw motion for each joint without type prior, and jointly optimize part-aware Gaussians with joint parameters through part motion blending. To introduce time-continuous geometric constraint for articulated modeling, we encourage Gaussians to be planar and propose a temporally consistent regularization between planar normal and depth through Taylor first-order expansion. Extensive experiments on both synthetic and real-world articulated objects demonstrate our superiority in generalizable part-level surface reconstruction and joint parameter estimation, compared to existing approaches. Project Site: https://sites.google.com/view/reartgs2/home.

翻译：关节物体在日常环境中无处不在，例如抽屉和冰箱。针对其部件级表面重建与关节参数估计，REArtGS 提出了一种类别无关的方法，利用两个不同状态下的多视角 RGB 图像。然而，我们观察到 REArtGS 在处理螺旋关节或多部件物体时仍存在困难，并且对未见状态缺乏几何约束。在本文中，我们提出了 REArtGS++，这是一种新颖的方法，旨在通过时序几何约束和平面高斯抛雪实现可泛化的关节物体重建。我们首先为每个关节建模一个解耦的螺旋运动（无需关节类型先验），并通过部件运动混合联合优化部件感知的高斯模型与关节参数。为了给关节建模引入时间连续的几何约束，我们鼓励高斯模型呈平面化，并通过泰勒一阶展开在平面法向量与深度之间提出一种时序一致的正则化方法。在合成与真实世界关节物体上进行的大量实验表明，与现有方法相比，我们在可泛化的部件级表面重建和关节参数估计方面具有优越性。项目网站：https://sites.google.com/view/reartgs2/home。