PROJECT TITLE :

Selecting Interesting Image Regions to Automatically Create Cinemagraphs

ABSTRACT:

A cinemagraph may be a novel medium that infuses a static image with the dynamics of one or several explicit image regions. It is in several ways intermediate between a photograph and video, and it has varied potential applications, such as within the creation of dynamic scenes in computer games and interactive environments. However, creating cinemagraphs could be a time-consuming process requiring high proficiency in photo-editing techniques. This text presents a unique framework for automatically creating cinemagraphs from video sequences, with specific stress on determining the composition of masks and layers in creating aesthetically pleasing cinemagraphs. Treating video as a spatiotemporal data volume, the problem is considered a sort of constrained optimization problem involving the discovery of a connected subgraph in video frames with maximal cumulative interestingness scores. The proposed framework accommodates multiple criteria describing qualities of interest in native image patches based on appearance and motion. Furthermore, the chosen regions are not restricted to bound shapes--the proposed approach facilitates capturing arbitrary objects. Experiments demonstrate the performance of the proposed approach. The findings of this study provide valuable data regarding various design selections for developing an straightforward and versatile authoring tool for cinemagraphs.