Efficient Inference in Fully Connected CRFs with Gaussian Edge PotentialsEfficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Philipp Krähenbühl Computer Science Department Stanford University philkr@cs.stanford.edu Vladlen Koltun Computer Science Department Stanford University vladlen@cs.stanford.edu Abstract Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or imag
