用神经隐式表示实现拓扑可变的形状插值，适合点云等非结构化数据。
4Deform: Neural Surface Deformation for Robust Shape Interpolation
- 基于欧氏空间连续速度场，支持自由拓扑变化的形变建模。
- 在噪声、部分数据、拓扑变化等场景下显著优于现有隐式方法。
- 无需中间形状监督，适用于真实世界4D点云上采样与高分辨率网格变形。
在计算机视觉中，生成非刚性形变形状之间的逼真中间形态是一项挑战，尤其在缺乏时间一致性的非结构化数据（如点云）和拓扑变化的情况下。大多数插值方法针对结构化数据（如网格）设计，难以应用于真实点云。本文提出4Deform，利用神经隐式表示（NIR）实现自由拓扑变化的形变。不同于基于网格顶点的形变场学习，本方法在欧氏空间中学习连续速度场，适用于点云等低结构数据。此外，训练中无需中间形状监督，而是通过物理与几何约束正则化速度场。通过改进的等值面方程重建中间表面，直接关联NIR与速度场。实验表明，该方法在多种场景（如噪声、部分数据、拓扑变化、非等距形变）下显著优于现有隐式方法，并首次实现了4D Kinect序列上采样与真实世界高分辨率网格形变的新应用。
原文摘要 · Abstract (English)
Generating realistic intermediate shapes between non-rigidly deformed shapes is a challenging task in computer vision, especially with unstructured data (e.g., point clouds) where temporal consistency across frames is lacking, and topologies are changing. Most interpolation methods are designed for structured data (i.e., meshes) and do not apply to real-world point clouds. In contrast, our approach, 4Deform, leverages neural implicit representation (NIR) to enable free topology changing shape deformation. Unlike previous mesh-based methods that learn vertex-based deformation fields, our method learns a continuous velocity field in Euclidean space. Thus, it is suitable for less structured data such as point clouds. Additionally, our method does not require intermediate-shape supervision during training; instead, we incorporate physical and geometrical constraints to regularize the velocity field. We reconstruct intermediate surfaces using a modified level-set equation, directly linking our NIR with the velocity field. Experiments show that our method significantly outperforms previous NIR approaches across various scenarios (e.g., noisy, partial, topology-changing, non-isometric shapes) and, for the first time, enables new applications like 4D Kinect sequence upsampling and real-world high-resolution mesh deformation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。