Co-segmentation for Space-Time Co-located Collections
This addresses segmentation ambiguities in dynamic event images captured by multiple photographers, but it is incremental as it builds on existing co-segmentation techniques with a new weakly-supervised approach.
The paper tackles the problem of co-segmentation in space-time co-located image collections, where ambiguities arise from multiple co-occurring objects, by introducing a weakly-supervised technique that uses a single segmented image as a seed and propagates local belief models. The method outperforms previous co-segmentation techniques on challenging datasets adapted for this novel setting.
We present a co-segmentation technique for space-time co-located image collections. These prevalent collections capture various dynamic events, usually by multiple photographers, and may contain multiple co-occurring objects which are not necessarily part of the intended foreground object, resulting in ambiguities for traditional co-segmentation techniques. Thus, to disambiguate what the common foreground object is, we introduce a weakly-supervised technique, where we assume only a small seed, given in the form of a single segmented image. We take a distributed approach, where local belief models are propagated and reinforced with similar images. Our technique progressively expands the foreground and background belief models across the entire collection. The technique exploits the power of the entire set of image without building a global model, and thus successfully overcomes large variability in appearance of the common foreground object. We demonstrate that our method outperforms previous co-segmentation techniques on challenging space-time co-located collections, including dense benchmark datasets which were adapted for our novel problem setting.