# Sparse data interpolation using the geodesic distance affinity space

## TL;DR

This paper introduces a novel sparse data interpolation method based on geodesic distance affinity space, demonstrating superior accuracy and speed over existing techniques, including EpicFlow, across multiple experiments.

## Contribution

The paper adapts the geodesic distance recursive filter for sparse data interpolation, providing a general, more accurate, and faster alternative to existing methods.

## Key findings

- Outperforms other interpolation techniques in qualitative and quantitative tests
- More accurate than EpicFlow in optical flow interpolation
- Significantly faster than EpicFlow

## Abstract

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.