We describe a method to automatically augment a watertight digital costume onto a person’s body from a monocular RGB image. When overlaying a digital costume onto a body using pose matching, several parts of the person’s cloth or skin remain visible due to differences in shape and proportions. In this paper, we present a practical solution to these artifacts which requires minimal costume parameterization work, and a straightforward inpainting approach. To our knowledge, our approach is the first to deliver plausible watertight costumes from RGB imagery only, and is compatible with mobile devices. We believe this can serve as a useful baseline for future improvements and comparisons.
The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.