Fast variational multi-view segmentation through backprojection of spatial constraints

We present a variational segmentation method which exploits color, edge and spatial information between an arbitrary number of views. In contrast to purely image based information like color and gradient, spatial consistency is a new cue for segmentation, which originates from the field of 3D reconstruction. We show that this cue can be easily integrated in a variational formulation and allows pixel-accurate segmentation, even for objects which are hard to segment. The use of inherently parallel algorithms and the implementation on modern GPUs allows us to apply this method to semi-supervised and completely automatic settings. On publicly available datasets we show that our method is faster and more accurate than the state of the art. The successful applications within a catadioptric measurement system and multi-view background subtraction shows its practical relevance.

► Color models from different images in a multi-view settings are fused in a geometrically consistent way. ► Segmentation is carried out in image space, yielding pixel accurate segmentations. ► Implementation on modern GPUs enables segmentation results at interactive frame rates.