In this paper, a novel unsupervised approach for the segmentation of unorganized 3D points sets is proposed. The method derives by the mean shift clustering paradigm devoted to se...
Marco Cristani, Umberto Castellani, Vittorio Murin...
We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
For designing aesthetic surfaces, such as the car bodies, it is very important to use aesthetic curves as characteristic lines. In such curves, the curvature should be monotonical...
We propose an advanced visual hull technique to compensate for outliers using reliabilities of the silhouettes. The proposed method consists of a foreground extraction technique b...
Hansung Kim, Ryuuki Sakamoto, Itaru Kitahara, Neal...
We present an intuitive, fast and accurate interactive segmentation method for visualizing and analyzing 3D medical images. Our method combines a general deformable subdivision-sur...