4Deform: Neural Surface Deformation for Robust Shape Interpolation

TL;DR

4Deform introduces a neural implicit approach for realistic shape interpolation that handles unstructured data, topology changes, and does not require intermediate supervision, enabling advanced applications like 4D sequence upsampling.

Contribution

It proposes a novel neural implicit method that learns a continuous velocity field for shape deformation, suitable for point clouds and topology changes, without needing intermediate shape supervision.

Findings

Outperforms previous NIR methods in various scenarios

Enables 4D Kinect sequence upsampling

Supports real-world high-resolution mesh deformation

Abstract

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.