The multitude of cameras constantly present nowadays redefines the meaning of capturing an event and the meaning of sharing this event with others. The images are frequently uploaded to a common platform, and the image navigation challenge naturally arises. We introduce RingIt: a spectral technique for recovering the spatial order of a set of still images capturing an event taken by a group of people situated around the event. We assume a nearly instantaneous event, such as an interesting moment in a performance captured by the digital cameras and smartphones of the surrounding crowd. The orderingmethod extracts the K-nearest neighbors (KNN) of each image from a rough all-pairs dissimilarity estimate. The KNN dissimilarities are refined to form a sparse weighted Laplacian, and a spectral analysis then yields a ring angle for each image. The spatial order is recovered by sorting the obtained ring angles. The ordering of the unorganized set of images allows for a sequential display of the captured object. We demonstrate our technique on a number of sets capturing momentary events, where the images were acquired with low-quality consumer cameras by a group of people positioned around the event.
- Event and action recognition
- Image alignment and registration
- Image-based modelling
- Motion capture and synthesis