BriefGPT.xyz
Oct, 2012
具高斯边缘势的全连接CRF的高效推理
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
HTML
PDF
Philipp Krähenbühl, Vladlen Koltun
TL;DR
本文提出了一种基于高斯核线性组合的高效近似推理算法，用于在完整的像素集上定义的全连接CRF模型的密集像素级连接，为多类图像分割和标注技术提供了显著的改进。
Abstract
Most state-of-the-art techniques for
multi-class image segmentation
and labeling use
conditional random fields
defined over pixels or image regions. While region-level models often feature
→