Joshua J. Ratcliff

Real-time Guidance Camera Interface to Enhance Photo Aesthetic Quality

This paper explores whether it is effective to use real-time on-screen guidance to help users take better photos with mobile devices. Using a three-camera array, we developed a photo-taking interface that provides real-time feedback on how to position the subject-of-interest according to a photography composition rule: rule-of-thirds. We conduct a user study to compare the aesthetic quality of photos taken with our real-time guidance interface against a static gridline interface common to existing digital cameras. Expert photographers and Mechanical Turk workers rate the aesthetic quality of these pairs of photos. Results indicate the photos taken with our real-time guidance interface have significantly higher aesthetics scores. This study shows the potential in using camera array, computational photography, and real-time guidance interface to help non-expert users take better photos.

Creative Transformations of Personal Photographs

The popularity of mobile photography paves the way to create new ways of viewing, interacting and enabling a users creative expression with personal media. In this paper, we describe an instantaneous and automatic method to localize the camera and enable segmentation of foreground objects such as people from an input image, assuming knowledge of the environment in which the image was taken. Camera localization is performed by comparing multiple views of the 3D environment against the uncalibrated input image. Following localization, selected views of the 3D environment are aligned, color-mapped and compared against the input image to segment the foreground content. We demonstrate results using our proposed system in two illustrative applications: a virtual game played between multiple users involving virtual projectiles and a group shot of multiple people who may not be available simultaneously at the same time or place created against a background of their choice.