Abstract. We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method...
"In this paper, we present a new variational formulation for geometric active contours that forces the level set function to be close to a signed distance function, and theref...
Chunming Li, Chenyang Xu, Changfeng Gui, and Marti...
Abstract. The Mumford-Shah model has been one of the most powerful models in image segmentation and denoising. The optimization of the multiphase Mumford-Shah energy functional has...
Segmentation-based approach has shown significant success in stereo matching. By assuming pixels within one image segment belong to the same 3D surface, robust depth estimation ca...
In this paper a heuristic segmentation algorithm is presented based on the oversegmentation of an image. The method uses a set of different segmentations of the image produced pre...
Juan Carlos Pichel, David E. Singh, Francisco F. R...