REArtGS++：基于平面高斯泼溅与时序几何约束的泛化性关节重建
REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
把高斯球约束成平面片，并用泰勒一阶展开在平面法向与深度之间建立时序一致正则，从而在未见状态下也能给出几何约束；这套「平面高斯 + 时序几何约束」可直接迁移到其他需要跨状态/跨帧一致性的动态或可动场景重建任务。
原文依据 we encourage Gaussians to be planar and propose a temporally consistent regularization between planar normal and depth through Taylor first-order expansion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论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，使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然存在困难，并且对未见状态缺乏几何约束。本文提出 REArtGS++，一种通过时序几何约束与平面高斯泼溅实现泛化性关节物体重建的新方法。我们首先为每个关节建模一种不依赖类型先验的解耦螺旋运动，并通过部件运动混合联合优化部件感知高斯与关节参数。为给关节建模引入时间连续的几何约束，我们促使高斯呈平面状，并借助泰勒一阶展开在平面法向与深度之间提出一种时序一致正则化。在合成与真实关节物体上的大量实验表明，与现有方法相比，我们在泛化性部件级表面重建与关节参数估计方面具有优势。项目主页：https://sites.google.com/view/reartgs2/home https://sites.google.com/view/reartgs2/home。
英文原文摘要 1313 字符
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 https://sites.google.com/view/reartgs2/home.