通过特征场学习凸分解
Learning Convex Decomposition via Feature Fields
把凸分解从逐形状优化变成可前馈预测的特征场学习问题：学一个连续特征场，再用自监督几何目标聚类成凸体，可直接用于碰撞检测、物理仿真以及跨网格/CAD/高斯泼溅表示的泛化。
原文依据 learn a continuous feature field that can later be clustered to yield a good convex decomposition
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文针对长期存在的凸分解问题提出了一种新形式，通过特征场学习实现，首次给出了面向开放世界凸分解学习的前馈模型。本方法能将三维形状高质量地分解为若干凸体的并集，而凸体并集对于加速物理仿真中的碰撞检测以及许多其他应用至关重要。核心洞见在于采用特征学习思路，学习一个连续特征场，随后借助由凸性经典定义导出的自监督、纯几何目标对该特征场进行聚类，从而得到良好的凸分解。该形式既可用于单形状优化，更重要的是，特征预测解锁了在大规模数据集上的可扩展自监督学习，从而首次实现了凸分解的开放世界学习。实验表明，本方法的分解质量优于其他方案，并能泛化到开放世界物体，以及跨表示泛化到网格、CAD 模型乃至高斯泼溅。
英文原文摘要 1102 字符
This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields, enabling the first feed-forward model for open-world learning of convex decomposition. Our method produces high-quality decompositions of 3D shapes into a union of convex bodies, which are essential to accelerate collision detection in physical simulation, amongst many other applications.The key insight is to adopt a feature learning approach and learn a continuous feature field that can later be clustered to yield a good convex decomposition via our self-supervised, purely-geometric objective derived from the classical definition of convexity.Our formulation can be used for single shape optimization, but more importantly, feature prediction unlocks scalable, self-supervised learning on large datasets resulting in the first learned open-world for convex decomposition.Experiments show that our decompositions are higher-quality than alternatives and generalize across open-world objects as well as across representations to meshes, CAD models, and even Gaussian splats.