Abstract

Scale variation commonly arises in images/videos, which can- not be naturally dealt with by optical flow. Invariant feature matching, on the contrary, provides sparse matching and could fail for regions with- out conspicuous structures. We aim to establish dense correspondence between frames containing ob jects in different scales and contribute a new framework taking pixel-wise scales into consideration in optical flow estimation. We propose an effective numerical scheme, which iteratively optimizes discrete scale variables and continuous flow ones. This scheme notably expands the practicality of optical flow in natural scenes con- taining various types of ob ject motion.