We present a photo slideshow system that automatically analyzes thematic information about the photo collection and utilizes such information to generate compositions and transitions in two modes: story-telling mode and person-highlighting mode. In the story-telling mode the system groups photos by a theme-based clustering algorithm and photos in each theme cluster are seamlessly tiled on a slide. Multiple tiling layouts are generated for each theme cluster and the slideshow is animated by intra-cluster transitions. In the person-highlighting mode, the system first recognizes faces from photos and creates photo clusters for individuals. It then uses face areas as ROI (Regions of Interests) and creates various content-based transitions to highlight individuals in a cluster. With an emphasis on content awareness, our system creates slideshows with more fluid, dynamic and visually pleasing structure compared to existing tiling slideshows [Chen06] and photo-to-video [Hua04] systems. Finally, the rendering of the slideshow is implemented in GPU, which significantly decreases the creation time of the slideshow and improves its quality.
展开▼
