4Deform: Neural Surface Deformation for Robust Shape Interpolation
This addresses a challenge in computer vision for applications like 4D sequence upsampling and mesh deformation, but it is incremental as it builds on neural implicit representations.
The paper tackles the problem of generating realistic intermediate shapes between non-rigidly deformed shapes, especially for unstructured data like point clouds, by proposing 4Deform, which uses neural implicit representation and a continuous velocity field to enable free topology changes without intermediate-shape supervision, significantly outperforming previous methods across various scenarios.
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.