Sparse data interpolation using the geodesic distance affinity space
This work addresses interpolation challenges for sparse data in domains like computer vision, though it appears incremental as it builds on existing geodesic distance principles.
The paper tackles sparse data interpolation by adapting a geodesic distance-based recursive filter, demonstrating superior accuracy and speed over existing methods like EpicFlow in three experiments.
In this paper, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem. The proposed technique is general and can be easily applied to any kind of sparse data. We demonstrate the superiority over other interpolation techniques in three experiments for qualitative and quantitative evaluation. In addition, we compare our method with the popular interpolation algorithm presented in the EpicFlow optical flow paper that is intuitively motivated by a similar geodesic distance principle. The comparison shows that our algorithm is more accurate and considerably faster than the EpicFlow interpolation technique.