RingIt: Ring-Ordering Casual Photos of a Temporal Event

Hadar Averbuch-Elor and Daniel Cohen-Or
Tel Aviv University
ACM Transactions on Graphics
Results 1 Results 2 Results 3
(a) (b) (c)

Figure: (a) Given a set of unorganized casual images capturing a dynamic event, we first (b) compute a full all-pairs dissimilarity matrix. Next, (c) we define a sparse refined dissimilarity among the KNN. Finally, (d) a spectral analysis reveals the ring order of the images.


The multitude of cameras constantly present nowadays redefined 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, e.g., an interesting moment in a performance captured by the digital cameras and smartphones of the surrounding crowd. The ordering method 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.


Click on the links below to view the ring-ordering and bullet-time displays of our casual datasets.



Paper (PDF)
Supplementary Material (PDF)

BibTex Reference

    author = {Hadar Averbuch-Elor and Daniel Cohen-Or},
    title = {RingIt: Ring-Ordering Casual Photos of a Temporal Event},
    journal   = {ACM Transactions on Graphics},
    volume    = {34},
    number    = {3},
    article     = {33},
    year = 2015,

Presentation slides

To appear later...


This work supported by the Israel Science Foundation.

Last update to the page: February 20, 2015.