Implicit Neural Surface Deformation with Explicit Velocity Fields
This addresses the need for unsupervised shape deformation in computer vision and graphics, offering a novel approach for both rigid and non-rigid cases.
The paper tackles the problem of predicting time-varying neural implicit surfaces and deformations between point clouds without supervision, achieving superior quality and efficiency compared to existing methods.
In this work, we introduce the first unsupervised method that simultaneously predicts time-varying neural implicit surfaces and deformations between pairs of point clouds. We propose to model the point movement using an explicit velocity field and directly deform a time-varying implicit field using the modified level-set equation. This equation utilizes an iso-surface evolution with Eikonal constraints in a compact formulation, ensuring the integrity of the signed distance field. By applying a smooth, volume-preserving constraint to the velocity field, our method successfully recovers physically plausible intermediate shapes. Our method is able to handle both rigid and non-rigid deformations without any intermediate shape supervision. Our experimental results demonstrate that our method significantly outperforms existing works, delivering superior results in both quality and efficiency.