CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequences
This addresses the challenge of non-rigid 4D interpolation for applications like computer vision and graphics, offering a novel method that improves accuracy and robustness over prior approaches.
The paper tackles the problem of interpolating arbitrary-length sequences of 3D point clouds into a continuous deforming shape, introducing CanFields which optimizes fine-detailed geometry and deformation jointly, demonstrating superior performance on over 50 diverse sequences with robustness to missing regions, noise, and sparse data.
We introduce Canonical Consolidation Fields (CanFields). This novel method interpolates arbitrary-length sequences of independently sampled 3D point clouds into a unified, continuous, and coherent deforming shape. Unlike prior methods that oversmooth geometry or produce topological and geometric artifacts, CanFields optimizes fine-detailed geometry and deformation jointly in an unsupervised fitting with two novel bespoke modules. First, we introduce a dynamic consolidator module that adjusts the input and assigns confidence scores, balancing the optimization of the canonical shape and its motion. Second, we represent the motion as a diffeomorphic flow parameterized by a smooth velocity field. We have validated our robustness and accuracy on more than 50 diverse sequences, demonstrating its superior performance even with missing regions, noisy raw scans, and sparse data. Our project page is at: https://wangmiaowei.github.io/CanFields.github.io/.