Video Interpolation using Optical Flow and Laplacian Smoothness
This work addresses video interpolation for computer vision applications, but it is incremental as it builds on existing mesh-based approaches like Li et al. with added smoothness constraints.
The paper tackles non-rigid video interpolation by introducing an optical flow method with Laplacian Cotangent Mesh constraints to improve local smoothness, achieving competitive results on benchmark datasets like Middlebury and Garg et al., and demonstrating application in 3D Morphable Facial Models.
Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data.