Design and Implementation of a Common Dataset for Comparison and Evaluation of Diminished Reality Methods.

Diminished reality (DR) is a technique to remove or inpaint real objects in a display. While DR is one of the active topics in the ISMAR community, a fair comparison between existing or emerging DR methods is difficult, that is, many methods rely on subjective evaluation that uses their own results to demonstrate their advantages. We, therefore, present a common dataset as a basis of the research for fair evaluations. In this article, we describe the design and implementation directions of the dataset. Our dataset is open to the public on the Web† (as of Oct. 9, 2017).