REArtGS++: 通过平面高斯散射的时序几何约束实现通用的关节重建
REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
AI总结：
REArtGS++通过引入时序几何约束和平面高斯散射，提升关节物体在不同状态下的通用表面重建和参数估计能力。
摘要：
关节物体在日常环境中普遍存在，如抽屉和冰箱。为了实现其部分级表面重建和关节参数估计，REArtGS引入了一种不依赖类别的方法，利用不同状态下的多视角RGB图像。然而，我们发现REArtGS仍然难以处理螺纹关节或多部件物体，并且缺乏对未见状态的几何约束。在本文中，我们提出了REArtGS++，一种新的方法，通过时序几何约束和平面高斯散射实现通用的关节物体重建。我们首先为每个关节建模一种解耦的螺纹运动，不依赖类型先验，并通过部分运动混合联合优化部分感知的高斯分布和关节参数。为了引入连续时间的几何约束，我们鼓励高斯分布成为平面，并通过泰勒一阶展开提出平面法向量和深度之间的时间一致正则化。在合成和真实世界关节物体上的大量实验表明，我们的方法在通用部分级表面重建和关节参数估计方面优于现有方法。项目网站：https://sites.google.com/view/reartgs2/home。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
